{"as_of":"2026-08-09T22:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d280da296744fda43c5ced593e00633b00b54aa27250146417cf339fa04deb86","coverage":[{"denominator":116,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T20:02:53.485837Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.07841/citation-record","integrity":"/paper/2606.07841/integrity","json":"/paper/2606.07841/citation-record.json","paper":"/paper/2606.07841"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"PosteriorDB.jl: A Julia package to work with posteriordb","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:0cf816c9f91dafa327fe86a1bfeed4594d30784d48593aa9f0e2ad4e090ca4a9","observation_id":"7bb24314-9ba0-4b2b-ad05-3d3567a740ad","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":"1607.06450","doi":"10.1007/978-3-319-32025-0","metadata_source":"pith","pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Layer Normalization","venue":"stat.ML","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","year":2016},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:b5662d8b98ec7ef149b943aca2f13fa983a0872c7fc67a4a94c6965c807d078f","observation_id":"d33599d9-0afd-425d-9e37-12a20202398f","resolution":{"observed_at":"2026-07-02T20:57:23.299060Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Online learning rate adaptation with hypergradient descent","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:74bd700116a83bde3ebc908322b8341ee643aab9999a442110c56bbf669aaa8d","observation_id":"704cbe98-e985-463c-8b15-b44e0a5b16f9","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Training neural networks for and by interpolation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:bb62cd32f79931177e278c3fd71bb014e5aa8d3a93ff05485c4e863820577f65","observation_id":"67e7efc5-9862-4e6e-9b8d-af42f44d6b80","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Julia: A fresh approach to numerical computing","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:a893bf15073050c6fa98b3278df7935dac97c2789b962a86e9bb65c4a8b8bff0","observation_id":"2067801d-6290-49a2-8a99-938c7c2579a9","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Variational inference: A review for statisticians","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:dbc694f016962ed482740ec4181a425c8d2b1baf76b68997bf44f532cf8a61e0","observation_id":"b0247205-b239-4a7d-8e76-841f3d72046c","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"On-line learning and stochastic approximations","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:04d0b64d559f7c00ab2595a77ed960623e9de526a754686d2ab016b0874ed9db","observation_id":"253c785a-6fed-4a95-8a30-d57aa4b82202","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Optimization methods for large-scale machine learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:d3c30fc42bbcedec458c9a53cb5d335818bb0dd1d5ddde51ba5a95b5b8bcd708","observation_id":"22f354b9-f2b8-44be-b659-47d9ae987384","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Quasi-Monte Carlo variational inference","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:9d55c363330f7d7cee1dc2aa8733ff424f3f93f2d6048c6fd9778145be74bcd4","observation_id":"995a031c-28ac-4389-8cb5-8e43c56baa66","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Importance weighted autoencoders","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:71eb7c5c569e81b5aad87a8cbf2e1f258a870e077ae0856a943c0954aa5bbb3e","observation_id":"7ec904ee-8901-4fe4-9c3d-2f18820486e2","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Sample average approximation for black-box variational inference","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:57964944a4f694d2802038862dd36b2e79d87c191e00858d035a9d40802a757e","observation_id":"3503c248-c47f-4a65-af44-df60f7277c0b","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"EigenVI: Score-based variational inference with orthogonal function expansions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:0369445c9f63be983428909e8feda3617483d0c3a468bf3c9687c3539ceb1ca4","observation_id":"c00a260c-e091-4d47-823d-dc5273101b85","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Batch and Match: Black-box variational inference with a score-based T. Campbell, J. H. Huggins, K. Kim, C. C. Margossian29 divergence","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:ccf25938e7f02f345afa8def32f8362c3b9bb68714ff100d024577fa1550df12","observation_id":"7c784a13-ca55-47c6-8c9b-530257f59edc","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Making SGD parameter-free","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:d82b737a022afa1eec6ebfff520edd633180d857a30f5a9ff69c87539da31ebb","observation_id":"860698ef-eb0b-437f-8634-3ade52995150","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Algorithms for computing the sample variance: Analysis and recommendations","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:830fc5810449f15c579ac7a06aa34b52cf7e2ef3e0d294bff197881498d478ee","observation_id":"f9a05077-a045-4047-93d4-ee159b2f6b84","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Symbolic discovery of optimization algorithms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:2cb0fea5f6764f33b807981c53920124537cb43e303273e8554c7413ae49fa21","observation_id":"73b3e85b-7242-4b38-97b5-999e3d5e81be","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Mechanic: A learning rate tuner","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:43a8b367da0c16d930b6af84b731e86846f88d1ceebf17ff461a4eab75cabaff","observation_id":"1619e1a6-8f55-4631-94e5-c608bf8759b1","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"The Helmholtz Machine","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:3a0da1f3cd94b96462da664c074820e439aa7e3d559fb5fdfe4150a7c6368e46","observation_id":"0384c369-d3dc-4bf8-8daa-daa8c3efc47d","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Big Batch SGD: Auto- mated inference using adaptive batch sizes","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:2c8e3e6458188b84ae71aaa484fa738ecb9295df7e3ab42a6d5c178f0f99a276","observation_id":"00a8e820-a263-4a5c-9c46-ceb58609c0a6","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:5315a02170a9ee76509c66e6655b5ca14ece0a87ef8354f0a4d209f8b7f74dff","observation_id":"198f2376-04a3-4cb4-8349-2f667d766af6","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Learning-rate-free learning by D- adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:3651e1a2221632de07a263f525d856692fe6ac2d9c64299bbc3bd57aae7ba04c","observation_id":"ee18858d-75b7-4c07-a522-1f5f07f6653f","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Robust, accurate stochastic optimization for variational inference","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:c9aba312a507c46de4e3d6f441429bd3d550583a9ce41ba0500d36b32f04ef2a","observation_id":"179f75d5-88db-4b61-a86b-28195185c4c3","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Challenges and opportunities in high-dimensional variational inference","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:ba38fffbaf1583eee5e7eab2961722ed768cc2da7883246200dd3d3a01887462","observation_id":"bb7201df-aaaa-4056-b593-901ebfe84669","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Forward- backward Gaussian variational inference via JKO in the Bures-Wasserstein space","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:b2ba68a0efc79a3078fa7bf1529b53993ca019924a0b0b40cd3dd96ee867dc74","observation_id":"2f8a9a74-c97a-41f7-8e76-50c16fc32b37","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Variational 30Default optimizers for variational inference inference viaχ-upper bound minimization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:03b51ba9fdf7c1de27aaf03b67a50598f6a2570f07dfe4d3d807c34e64f3e8c0","observation_id":"0dce2761-e207-439c-9332-232101b4bb4f","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"bridging the gap between constant step size stochastic gradient descent and Markov chains","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:a492aa3426ffd8bb29647720d1e6263294a75e4dddcf51ab01554167e9f57639","observation_id":"fd355b34-44f7-40d2-a1ce-3dd95bd32110","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Provable gradient variance guarantees for black-box variational inference","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:2a3baee8a76d758493f837147de085974119abcef43cfd86e78c385efe471990","observation_id":"e3477668-6e4f-4dac-8d91-b018c01a8750","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Provable smoothness guarantees for black-box variational inference","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:59dbe2049358b711c3a56dbbe8ac6e46cd9e0fe84c62e0e141684e2e9088608e","observation_id":"b5c936cb-ca6e-4cb5-a8ba-13345e0058b4","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Provable convergence guarantees for black-box variational inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:efa05f13e5274c85b26d2416ba118e721bd3eb1db45a2ecba58e33cdfebe8b7f","observation_id":"9c0a4aeb-cf12-4632-b96b-831afa2d1787","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Importance weighting and variational inference","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:223a16b8a9a0e6f0f3153d9ffdc25dfff3f96b53294958924c87f4c93598389a","observation_id":"b98c08f7-5693-470c-a403-b8995c7dee1b","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Divide and Couple: using Monte Carlo variational objectives for posterior approximation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:a58d0c085db9869a45e24dac3a5efd5a1460f3a5f36d60c30bb5857460578b17","observation_id":"20cc0a66-449f-424c-98f1-c2222d07a2b0","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Adaptive subgradient methods for online learning and stochastic optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:231b521c019c1439e7925070283df0ad3786791008746b9a0111db3752924fc4","observation_id":"6fef75ce-d353-45b6-bf6e-772dcfe3aba2","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Batch means and spectral variance estimators in Markov chain Monte Carlo","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:965397913ba01d6629bf8d69264a801cb8eb26b96e4d7968c58f98b0c47ac88e","observation_id":"aefc05df-b5ec-4972-a83f-3277ad36f83e","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Multilevel Monte Carlo variational inference","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:117861aee8177e84f5a56dbbf1444361ca82982452ec21f004f363731e89c45a","observation_id":"7616c9d4-dde8-4ee0-a578-1bc068d05143","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Don’t be so monotone: Relax- ing stochastic line search in over-parametrized models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:442112f045c618d8fa79a988c343259afbe9685072697336a2411b8e99d99f90","observation_id":"55b9b324-665a-44d4-9f9e-301403323923","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Empirical evaluation of biased methods for alpha divergence minimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:cf5d0836eea1dc24532df0c1198a32e56b7aab882c87d052301b45b6f46121ca","observation_id":"3d5be7d1-39f2-4b52-80b2-a08639cb5600","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"MCMC variational inference via uncorrected Hamiltonian annealing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:45ba69577714003916be050d196d3573cdd81b104358ada420b77a761967e638","observation_id":"6e914b24-d866-4792-8ebf-9d6d4b992573","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"On the difficulty of unbiased alpha divergence minimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:a6d5cce556d57b83ac96c34e8a9cd5bf9d5911e8c9190f4dfe6cb4e0975eb160","observation_id":"fcbb7a63-2fb1-496b-a3af-eb7b9364ce83","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Inference from iterative simulation using multiple sequences","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:b058f34e9a78a92618926702f2082d445b42ee6ad1a46470eeb7617b74667784","observation_id":"db08ba97-85b7-4cda-ae49-64e1825b1e04","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Black box variational inference with a deterministic objective: Faster, more accurate, and even more black box","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:b205d1f96cca6d4e428bdbf74f0d5f5c33a0ef7a4f4986a3615cd5d66ee3fc96","observation_id":"6b38a50b-406f-42a5-997d-6f85a40c2cc1","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Practical variational inference for neural networks","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:22773b7aab7ff69498e584516c6aad27a0c7c775a597afb815bdf62352046566","observation_id":"c7c3de64-1948-4e52-ab6c-d125b1d4a9c4","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Shampoo: Preconditioned stochastic tensor optimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:24cffa4910e2e3f1f67c497bc314e62e397995ffbaf65615f67446624edb34ed","observation_id":"5dc5f5ba-fb9c-4c6d-b832-76802ddbb3f5","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.00313","last_updated":"2022-08-02T17:48:25Z","snapshot_observed_at":"2026-07-06T07:49:44.506891Z","submitted_at":"2019-05-01T13:47:40Z","title":"Revisiting the Polyak step size","version":2},"cited_work":{"arxiv_id":"1905.00313","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1905.00313","snapshot_observed_at":"2026-07-04T06:59:37.573960Z","title":"Hazan and S","venue":null,"work_id":"1fafe5d3-69fe-46c5-b51a-9dfe1038d907","year":1905},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"cited_paper":"/paper/1905.00313","citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:1c0541f6ae2d39d9af8bdba011210c1c5658452a503b1caa9c400410845072ef","observation_id":"55cc2e41-8829-4821-a7d7-c4d5910f1f3f","resolution":{"observed_at":"2026-07-02T20:57:23.296734Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:a7b288801c0e72c6cf93280c8827f8e9dbc7fd604f7d25d5f65620d0f11380f7","observation_id":"b3a0f799-1512-4fd7-b79f-19a6e8aa0640","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Black-Box alpha divergence minimization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:11a9b1c5991ca75bf09a2b8e28a3bc5e0eda5a37edcc1bcb769c8315346c2b12","observation_id":"02e4076e-e458-4f57-a0d4-de20101b699c","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Keeping the neural networks simple by minimizing the description length of the weights","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:7e460162be7f815a00624cd511d14fd2b213d9eccb305b2d373bef417ba74630","observation_id":"915410b9-4063-4cbc-9974-bc736a585d1d","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Perturbation analysis and optimization of queueing networks","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:d3b29e9b699f412bf9d42a08d3693ac29ff6a4137cce2393526b836ec4d4e8af","observation_id":"9d46ff2e-3ff2-44f5-96a8-5b3874ceab05","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Validated variational inference via practical posterior error bounds","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:f620e08376f07f7736f97718af101f03e2953a659bb0a0fa5be286bc9c3a7d11","observation_id":"20ce6e99-4c80-4ff3-b772-3c2c8dfc8155","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08235","last_updated":"2017-02-27T11:16:54Z","snapshot_observed_at":"2026-08-02T07:17:14.537608Z","submitted_at":"2017-02-27T11:16:54Z","title":"Variational Inference using Implicit Distributions","version":1},"cited_work":{"arxiv_id":"1702.08235","doi":null,"metadata_source":"pith","pith_arxiv_id":"1702.08235","snapshot_observed_at":"2026-07-02T20:57:23.300337Z","title":"Variational Inference using Implicit Distributions","venue":"stat.ML","work_id":"0c346fa0-b90f-412a-99f7-805a463a1d5f","year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"cited_paper":"/paper/1702.08235","citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:c33f2e4c5af7f22af93c2a941e559f1e07202abdc73f3742f90f4bf007b553cf","observation_id":"e55a1678-db42-4848-9f0e-5f082cc584b8","resolution":{"observed_at":"2026-07-02T20:57:23.301455Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"DoG is SGD’s best friend: A parameter-free dynamic step size schedule","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:402d9d11ff9f666ea0c6171c2abe8e788da11cf9274dc172f55abd9f31004dc7","observation_id":"fc9f941d-b59d-4bab-a51e-56cd17ad9856","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Accelerating stochastic gradient descent using predictive variance reduction","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:506b40b69be92b869ee3361bce1c26b93c9166b0b93e0b644749e6928abb140e","observation_id":"112f47fc-63d7-4d45-b33c-0aa21d3ed220","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Muon: An optimizer for hidden layers in neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:a5f1af012ced1ca7eb2407996c2e887a98c76683e5062f9045f8cf1166e22730","observation_id":"e03c0fe8-b8df-4912-893a-d7bba84ef00d","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"An introduction to variational methods for graphical models","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:de0f149b7c1a978ed19399cb0877c50c07b52b0e474b4b1457a95776d86d8934","observation_id":"e464c5e2-ec83-487d-ae8c-d9fa72f6abfb","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"DoWG unleashed: An effi- cient universal parameter-free gradient descent method","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:42124a435eb16dd4c179ce7febeff6ff52cd5e09ac3dad2c368fe1b711ca1683","observation_id":"e658d7f6-ec94-4703-8652-1e227aa5c8bc","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"The Bayesian learning rule","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:4618fbb0fb2bc1a50f728be4d0ede9557ba7f2c2b0153d5f76f42c5e7fa90c81","observation_id":"a0408f92-a13e-4252-8250-d7cde2b988a4","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Linear convergence of black- box variational inference: Should we stick the landing?","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:755788ccc1a50533b8d4548dd2291486b93a175ff112917601d791006aec5a06","observation_id":"ff3fd9e8-f75f-4466-aff2-1f8a89cec362","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"On the convergence of black-box variational inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:e0cada18fa08c66c00718ac45cba53a6c2727589517fea7c2cf8c538f406ab8c","observation_id":"d0d4f03f-650f-47dc-8b1d-844613acab5b","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"A guide to sample average approximation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:fc73d5bad342e9f0831cee373212ac2be5967eec09432ffabe8fdd8e7510640e","observation_id":"2ca9014b-8603-48cd-bd44-52bafc186920","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:8dce969730ecae48931d664872883b24d7a64548a360937e4260aebb9c956f6c","observation_id":"d073021d-2fce-4289-ab8a-b00946255548","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Auto-encoding variational Bayes","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:330fb3a0cc91b18f27ecf33c6db9915dae6b63744cca6a9f885630b4ae46831f","observation_id":"de32b6ba-e932-46d6-b56e-06b976dfb0fe","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Automatic differentiation variational inference","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:85a3000c2ab7c0c050bc2a9099dff9b2fa869362643c7dbde2c12ed0ddcc9f60","observation_id":"e448df27-46d1-4016-b296-3436af9c4b79","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Optimization guarantees for square-root natural-gradient variational inference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:3df8cea954bcdd8c10d3a60ce46309237f8ca52a01769b1fbc31f7f5a1cfbab0","observation_id":"812a9dc2-7814-4d6a-9d95-9b8041c98d52","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Varia- tional inference via Wasserstein gradient flows","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:253d9790407019a6eecb4daf36ca6e209aed0f7b8594c48bc49da27b95012576","observation_id":"8de5267f-eeba-4f0a-8b21-c4584ec9c01f","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"A stochastic gradient method with an exponential convergence rate for finite training sets","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:4a7370a5108d748df1cd33bf43e32df070b6e7a60de6a1eee8de1c12f7adbc21","observation_id":"ec24212e-de98-483a-88f1-67cf13047bb5","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Rényi divergence variational inference","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:6278cf2d72a00664ea57da722c506829757e7e24d6d60ac0f7bc37fcb3b41f2b","observation_id":"bc280f19-b8ae-4ece-9770-89bb516e28a1","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Fast and simple natural-gradient variational inference with mixture of exponential-family approximations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:f656e656d3bac4642164f336aa42551ddddf4ad9dc8bb59b998a97b5862343f8","observation_id":"604feac3-820b-4af3-8e6b-522faa349a13","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Batch size selection for variance estimators in MCMC","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:79f89f38ef371dc5868b9f509b699c17eb14ae167eb4988a7d8a16d8b4c4a7c7","observation_id":"0c45f499-7ee1-4cc2-9b21-59d0a3a3a38d","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Stochastic Polyak step-size for SGD: An adaptive learning rate for fast convergence","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:c0b41fcbe13ee3dd648d26bf2006744cbdbfcc655f1ea9c5c75617a47c118acf","observation_id":"fe208f39-5796-4f21-84f7-afc649c9f617","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"The power of interpolation: Un- derstanding the effectiveness of SGD in modern over-parametrized learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:a07679de2664c34eb85ff1fd0840997a1b81951436dae5bf076fcf388edfb16a","observation_id":"f335ad2d-db64-487f-a30d-169a8d4f4469","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"posteriordb: Testing, benchmarking and developing Bayesian inference algorithms","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:7267ea4808c30421599231e063cdd0083fe544c4def0ecae1cf47c5796e947fb","observation_id":"602a4f83-bb57-41d6-b2c7-7e2e20b64fb4","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Torsten: A platform for Bayesian inference of pharmacometric models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:b9bfef2ccab15a732fbac21e75b902bfe0b607d98d2e196fb861d373e643acdd","observation_id":"3e5bf85a-9aca-4492-9131-b35566fc83cf","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Expectation propagation for approximate Bayesian inference","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:43f93f18bc70568a4922d0b7a04bc4fd4199829b67305b59ddd3bde29380cbc7","observation_id":"dcede6ab-3b70-4d7e-8571-25ccc707f8e4","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Variational Inference with Gaussian Score Matching","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:6dd5abfd413a33599e73d64d21ce5c1e1c951e299f3623004c82fa40c7844090","observation_id":"9a888c9c-2ecd-4bbb-a2e9-116d3cf1f1fe","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Monte Carlo Gradient Estimation in Machine Learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:c37d7a377c821d2372ac7ee5eeee855241f25407c405d1945a92b57c32f9b827","observation_id":"7a1091ce-1e5e-48c5-a57d-35aec4fa87f6","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:2c968301769f3ce4b31cc7ccf862fb0d38dc1443132f5fe4cbbe90524b162b1a","observation_id":"fba658eb-54c1-42ed-b0f4-9e1a217ad2e1","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Rectified linear units improve restricted Boltz- mann machines","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:676bf4bc43298feb8278a7a10cd8373c45bdc0a69a2e550b23ea8c8e9b604d7a","observation_id":"ebc400fb-0391-470a-a6b1-ed24aff6e6b3","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Gaussian Variational Approximation with a Factor Covariance Structure","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:f0a801827fcb3fee1babd3282ee78fcd95e9bf17841fe93266855f0d747fa45f","observation_id":"b2d1b7b0-e139-4d94-b4bf-7f117b984faf","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.00236","last_updated":"2021-01-30T15:05:34Z","snapshot_observed_at":"2026-08-09T10:30:00.447486Z","submitted_at":"2021-01-30T15:05:34Z","title":"Parameter-free Stochastic Optimization of Variationally Coherent Functions","version":1},"cited_work":{"arxiv_id":"2102.00236","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2102.00236","snapshot_observed_at":"2026-07-04T16:29:56.943866Z","title":"arXiv preprint arXiv:2102.00236 , year=","venue":null,"work_id":"76512e50-b571-4c65-a26c-171bca1d3390","year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"cited_paper":"/paper/2102.00236","citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:b6c2164954627bcd70685d2f20161887470861600060fe60bea266d9d0036f45","observation_id":"1f4cf38e-df62-4d2f-86e7-184c0ac2b018","resolution":{"observed_at":"2026-07-02T20:57:23.291452Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Training deep networks without learning 34Default optimizers for variational inference rates through coin betting","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:82877ac15a649a5c4b9a2a13adbe51e1929ca04a723d3770d7ab49e32798a251","observation_id":"81892e46-64cf-4c22-bb79-fe02ba15cc2d","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"R package","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:12063630be35ef02ea835d0a64e8894041fba6f623c8788500b8bd096065b3a8","observation_id":"45dd343e-9213-4979-a419-375b36d73512","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Explorations of the mean field theory learning algorithm","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:3a22480fcbf5c1155f4c65cfe5dcca2701115b09040ffa78c2f70d147fbdc739","observation_id":"28e31af2-badb-4cc1-a5d6-1282fb99765f","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"On the determination of the step size in stochastic quasigradient methods","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:7c28c1d5d2b0d699238e8857d7880bf2728c7422f6c57eaf5ac69bd31c1a9c51","observation_id":"33d12e04-df72-47af-b23d-9f87c7e6c2c0","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Acceleration of stochastic approximation by averaging","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:55f21408a4630c2c6aacbe5dc28686a73b0a6a92caff925ce0af4e2c1c012583","observation_id":"624c7bd8-4b9b-4c04-8438-3939538c1964","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Blackboxvariationalinference","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:2cba95f445f5714d6ab187c755a3bb5d2f2b026c573828e85e7bce9f3a1bd822","observation_id":"3c45809e-4f90-4658-8919-4f8b68cfd979","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Hierarchical variational models","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:67fe5257fb14ca9486614f66a4b2ec5b1eb0297c17fc812678830579531f22d5","observation_id":"a1dcc534-197e-4a50-b39f-febd2c88e52a","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"On the convergence of Adam and beyond","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:92a9d5e1d8cc1036757c014a2ba8eac0d32a29a867aeb1a33e2fddf98036fa8f","observation_id":"e8e965bd-7b75-45dc-b568-01202d32aacf","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Variational Inference with Normalizing Flows","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:4cb237b5215929e9b28f404d46df965c97ccc534fd3e55b6f0400fac05a405e0","observation_id":"427c0462-5c5a-4a53-8a42-13da741a1d6b","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Stochastic Backpropaga- tion and Approximate Inference in Deep Generative Models","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:15e61f211d3b8bb2ad93669419488add110751b70d2ed2cc1632b7bae88ac8ae","observation_id":"43ac5cd0-a71a-4fdd-a87f-6c3c07fea050","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"A stochastic approximation method","venue":null,"work_id":null,"year":1951},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:fdc76dddc198a0ab46a5d9b612a504ca49721cebd11da82385175dcd0c2ac210","observation_id":"06b391e6-d3df-4f0d-b845-38f63c27bf6d","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:65e33b5e781e14405929834fb6aeee97edb74afdf26ac556a9fb15a08e4b6a72","observation_id":"01dbe5a4-8ca9-4e17-aaa7-714d7ec84ea2","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Sticking the landing: Simple, lower-variance gradient estimators for variational inference","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:046a7ff0089b11cb54c3db65e28d8cbe2681306d66a5d653c8ce362b5a7ef1ff","observation_id":"64ce123a-e0d0-4cfe-99f6-fba6753e9725","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"BridgeStan: Efficient in-memory access to the methods of a Stan model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:885b179f6ac9a6d4515d913040131b33a75b9b730f5dd804f64258d6a7653c72","observation_id":"7aa1f528-8d85-4ad1-ab56-988d3afd7a31","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Sensitivity analysis of discrete event systems by the “push out","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:3d64b9512079b9949a62052db9bd949b2f0955391b9dee5816f1204aef23e37f","observation_id":"f41e12c4-c650-4a9a-a6f1-49a3b2083cfc","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Markov Chain Monte Carlo and Variational Inference: Bridging the Gap","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:06fc2a942f38b1364cd9270241d945fc829b020ee1a545a80cb6103eb41cf562","observation_id":"23558ea4-ab0b-42a9-99de-73d2686a4eea","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Mean field theory for sigmoid belief networks","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:bf34a8d4b895f54d1776b079e1fa198e7b1e7e90dca04a89e34f09eeb1ee47fd","observation_id":"2f9b09e3-1626-44e0-b833-0af4e284d37d","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Descending through a crowded valley—Benchmarking deep learning optimizers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:851816aae29905f3465eeb24ef5a7d4f6010df541bc901223428df02323665ea","observation_id":"4558e435-290d-41fc-8794-a428bbda8b92","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Stan Reference Manual, v2.38","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:d8c807d706abe05b96f9cc341ac9f603dd549c2309c09e424921b3f1eac56c55","observation_id":"9d3052d3-5fe5-4a67-9168-2b039638c3ce","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Analytic natural gradient updates for Cholesky factor in Gaussian variational approximation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:46ca7accc680cca5dcc11c91d6799920b82516d5725010fdd39f7c89088a8e1c","observation_id":"da64207c-2f92-4471-9c7e-c8400a643176","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Gaussian variational approximation with sparse precision matrices","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:17aa6abb31f1ad10f460ed2b5689d8e24de6a86c59d345c458a9851c8181b13d","observation_id":"028277a5-a7c3-46ff-a8cd-6e518e81fd19","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:02:53.485837Z","title":"Doubly stochastic variational Bayes for non-conjugate inference","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-06-27T20:02:53.485837Z"},"links":{"citing_paper":"/paper/2606.07841"},"observation_digest":"sha256:4cb9697c812b5fd287522508ddcb70d995522724ace38f499d680b9ca7c32cff","observation_id":"1bee595d-ade2-41ad-be0b-376bf0a80434","resolution":{"observed_at":"2026-06-27T20:02:53.485837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.07841","last_updated":"2026-06-05T21:04:12Z","latest_version":1,"primary_category":"stat.CO","snapshot_observed_at":"2026-08-09T11:00:19.121317Z","submitted_at":"2026-06-05T21:04:12Z","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":96,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":116},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 100 of 116 outbound references and 0 inbound Pith citation observations for arXiv:2606.07841."}