{"as_of":"2026-08-16T19:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:30c518fa929c62e5c79946b0681e4815953181b61eb9aa1a4e80c4542c3563ce","coverage":[{"denominator":75,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":75,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:47:48.232661Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2412.13928/citation-record","integrity":"/paper/2412.13928/integrity","json":"/paper/2412.13928/citation-record.json","paper":"/paper/2412.13928"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.517327Z","title":"Efficientconstrainedsamplingviathemirror-langevin algorithm","venue":null,"work_id":"9acfa67b-2e1a-4095-b160-4f3f4524fa4a","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.846110Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:1fd3d06090a9961650a5d249662b7aaf28c3c709727d5db4b487161cf02d6757","observation_id":"c953767f-15fc-4129-af3c-10ee7ee88bcd","resolution":{"observed_at":"2026-08-11T12:47:49.525639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:47.851690Z","title":"The fast Johnson–Lindenstrauss transform and approximate nearest neighbors.SIAM Journal on Computing, 39(1):302–322, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.851690Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:0f49ff812b871b0b79b28436e381b99d64f26c10ac4d03113b229f7649fbed9c","observation_id":"d53601b6-cfcb-46e4-96ab-9818dd7ac765","resolution":{"observed_at":"2026-08-11T12:47:47.851690Z","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":"2026-08-11T12:47:47.857558Z","title":"Springer Science & Business Media, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.857558Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:539c9088f4692cc865019eca124d4dcef222bc318beac035d26e0745db0067ff","observation_id":"10ea95b9-27d6-4e1d-abbe-54591b0f36de","resolution":{"observed_at":"2026-08-11T12:47:47.857558Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.477837Z","title":"High- dimensional sgd aligns with emerging outlier eigenspaces","venue":null,"work_id":"5b41ee9d-3f61-400e-9937-6510a2e4a97b","year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.863880Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:cb347a43e2e57348e11a7e35eb3a2ac11883696e0a236e3e272dcd0b03acccc3","observation_id":"8b344bd8-ea91-4f4d-a74c-84212a13c441","resolution":{"observed_at":"2026-08-11T12:47:49.483281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07542","last_updated":"2024-03-29T05:03:00Z","snapshot_observed_at":"2026-08-16T14:53:03.042571Z","submitted_at":"2023-10-11T14:46:55Z","title":"Fast Sampling and Inference via Preconditioned Langevin Dynamics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07542","snapshot_observed_at":"2026-08-11T12:47:47.870006Z","title":"Fast sampling and inference via preconditioned Langevin dynamics.arXiv preprint arXiv:2310.07542, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.870006Z"},"links":{"cited_paper":"/paper/2310.07542","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:3d93c6a2df5068632d5fc6bcd0251a45631d7fc0d5fd1fbee11be12d215780ab","observation_id":"1d65d0d9-40bd-40f1-a1df-c4dcd9e3d982","resolution":{"observed_at":"2026-08-11T12:47:47.870006Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.462030Z","title":"Efficientgradient flows in sliced-Wasserstein space.Transactions on Machine Learning Research, 2022","venue":null,"work_id":"91e59951-1bd1-4ae0-a268-406d49fa577f","year":2022},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.875472Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:2201446d33addcb3d02d68ca6c713822e1d92a93bef9704bdf42561d325eb28e","observation_id":"ef26b072-850e-4796-ab25-7160cd5a0996","resolution":{"observed_at":"2026-08-11T12:47:49.467800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08938","last_updated":"2024-11-18T20:56:37Z","snapshot_observed_at":"2026-08-16T13:43:25.639105Z","submitted_at":"2024-06-13T09:07:22Z","title":"Mirror and Preconditioned Gradient Descent in Wasserstein Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08938","snapshot_observed_at":"2026-08-11T12:47:47.880622Z","title":"Mirror and preconditioned gradient descent in wasserstein space.arXiv preprint arXiv:2406.08938, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.880622Z"},"links":{"cited_paper":"/paper/2406.08938","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:889e7c2e91c960d9238c056725d5482db9ee1069eaab108c3f1c3633058eb42e","observation_id":"152b93ea-9001-4110-adae-057fd4557ac3","resolution":{"observed_at":"2026-08-11T12:47:47.880622Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.444740Z","title":"Sliced and Radon Wasserstein barycenters of measures.Journal of Mathematical Imaging and Vision, 51: 22–45, 2015","venue":null,"work_id":"3b1bec08-645b-4c2b-885f-462caca76ffa","year":2015},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.885467Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:5e4601f2824843631d6bfeaf09297c7e98822810b3054b870174cf7567820ec0","observation_id":"46a8ba85-88ab-4c93-a26b-892b1e297881","resolution":{"observed_at":"2026-08-11T12:47:49.449282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:47.892172Z","title":"Finding frequent items in data streams","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.892172Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:1b30be45063fbb9fff8669ba8dba6bff66776e1d10c79372fb9db825443b180e","observation_id":"f09be30b-91ff-4fa3-a0c2-dea3f10678d2","resolution":{"observed_at":"2026-08-11T12:47:47.892172Z","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":"2026-08-11T12:47:47.897253Z","title":"Exploring low-dimensional subspaces in diffusion models for controllable image editing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.897253Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:4ac7e4b0cc61a0e6c9f1d3d96a7d18d31d75c39ccf997c8a4e91d20d19c5117c","observation_id":"f83abb2f-f733-4ba1-8537-5b5367417cfd","resolution":{"observed_at":"2026-08-11T12:47:47.897253Z","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":"2026-08-11T12:47:47.901605Z","title":"Improved analysis for a proximal algorithm for sampling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.901605Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:bed05922ebb0b007469ff08417df2c880d036100f8f3db9feca8d9f1b57bad7e","observation_id":"80c6bdd1-d13d-4d40-9fed-4e95fbd6e9e1","resolution":{"observed_at":"2026-08-11T12:47:47.901605Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.406961Z","title":"Log-concave sampling","venue":null,"work_id":"33ad8ccc-1c0e-4e6c-8368-d7df298acab7","year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.906226Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:8c543ae318a6156f59722729f0a2d76bb8b050ed7ed853ec3fd138d452852dfe","observation_id":"db809801-5086-4e78-b45e-9ae7d7ada28c","resolution":{"observed_at":"2026-08-11T12:47:49.413280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.383731Z","title":"Exponential ergodicity of mirror-Langevin diffusions","venue":null,"work_id":"404315ca-6682-434b-bc1b-ddba077ac9ea","year":2020},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.911905Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:3179a9587680c7d2ffab66bc2764ed8ab9edb6eec9a844e0691de6a6cdc61b86","observation_id":"b97a66b9-2b3b-4b90-9f01-0ad9c9b952d4","resolution":{"observed_at":"2026-08-11T12:47:49.393714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.369413Z","title":"Differential privacy dynamics of langevin diffusion and noisy gradient descent","venue":null,"work_id":"46332bf8-ab20-4b5c-bb9b-bf3af38d5317","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.917181Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:e0a22b1d600ea5221fad89d5f1d8432a4bab4edef365b0f60bae6a0b9db53c44","observation_id":"172a6fb2-420e-4ddf-9523-2b980e6338c2","resolution":{"observed_at":"2026-08-11T12:47:49.374656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.355344Z","title":"Gradient descent with low-rank objective functions","venue":null,"work_id":"dbe1b15a-91e1-4e24-8f88-ed77423bb93d","year":2023},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.924905Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:198ac5264b03d5c6ee0f784526cf5ecb0747e73293e78b8909cdba7bd1febffe","observation_id":"04521418-7e0d-43fc-97c9-650f1277ed97","resolution":{"observed_at":"2026-08-11T12:47:49.360710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.328994Z","title":"Low-rank gradient descent.IEEE Open Journal of Control Systems, 2023","venue":null,"work_id":"dab42a33-4edc-4189-8b8a-360847c0da35","year":2023},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.936014Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:e3e3c94a57937b44353f1b2a9cbb4b38fc02f26604671e5002bfb1b27af51f1c","observation_id":"4603cb27-423f-445a-88a0-cc2e9507c583","resolution":{"observed_at":"2026-08-11T12:47:49.335177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.309384Z","title":"User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient.Stochastic Processes and their Applications, 129 (12):5278–5311, 2019","venue":null,"work_id":"d1af9466-ba5f-42ec-833f-643099a23833","year":2019},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.940845Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:6be1eed6a963a3dfcdb44563bce52a95b4e9ea28669b391fbf1b6d63aef77f83","observation_id":"968cde04-3d14-4a3b-a51b-982af99ada4e","resolution":{"observed_at":"2026-08-11T12:47:49.315181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.295194Z","title":"A sparse Johnson–Lindenstrauss transform","venue":null,"work_id":"142598d2-bf44-4d4c-8f49-49b23d95ae1a","year":2010},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.947103Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:3b2ac3e4841ae917482107d35ec1e21a2527622d82113fc0c3c90b01d47f9516","observation_id":"dc1afdfb-9160-403f-b566-f51af97d54cb","resolution":{"observed_at":"2026-08-11T12:47:49.300147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.279183Z","title":"Langevin monte carlo: random coordinate descent and variance reduction.Journal of machine learning research, 22(205):1–51, 2021","venue":null,"work_id":"abf7c110-c5b1-4c2e-84d5-4b4b25e84440","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.953785Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:887862a75b7542a30fc461de9b6a784f92e26df0303e21934bca1f4abf17887c","observation_id":"0ca7af8a-a575-4484-bc22-8940b55bae09","resolution":{"observed_at":"2026-08-11T12:47:49.285233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.263254Z","title":"Random coordinate Langevin Monte Carlo","venue":null,"work_id":"055671bf-097c-4142-acac-a9420b74d898","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.962173Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:37c3c3183a373e32e9bb52c3fd58c291ea7d82e468d384114a3941ae4bdce3bc","observation_id":"84ea24f5-e3ad-4de9-b071-35a1e6b74d30","resolution":{"observed_at":"2026-08-11T12:47:49.267469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:47.967602Z","title":"Adaptive subgradient methods for online learning and stochastic optimization.Journal of machine learning research, 12(7), 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.967602Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:5da540e62f37cc3765dba90fa085e0b23754c2617a0ea0be7692195c98353054","observation_id":"123cc231-9319-408f-b63c-9561bf263489","resolution":{"observed_at":"2026-08-11T12:47:47.967602Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.218204Z","title":"High-dimensional bayesian inference via the unadjusted langevin algorithm.Bernoulli, 25(4A):2854–2882, 2019","venue":null,"work_id":"3fe3faa4-a6e3-492b-a46c-195703e3379f","year":2019},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.974538Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:40a7ab6d84a1c3d64fa3826b58643282d83722503dd1ea7f32a35bd37262579a","observation_id":"bcbf14b8-eaca-43f4-85d4-b770b935c4f9","resolution":{"observed_at":"2026-08-11T12:47:49.224172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.194039Z","title":"Analysis of Langevin Monte Carlo via convex optimization","venue":null,"work_id":"95f40458-294c-4a3c-861e-5f5cdf53f6fc","year":2019},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.980016Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:0090683352acc668efc384a3ae40d0c61a35e5dcbf46bf5638927abc27ca45ee","observation_id":"03ab85fa-5127-4b8f-907f-4922ec248e93","resolution":{"observed_at":"2026-08-11T12:47:49.201664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.174816Z","title":"Sketchy: Memory-efficient adaptive regularization with frequent directions.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"affe70f5-46e4-46c4-9fc9-b8bfe553e1bd","year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.985256Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:0dd3464483a1fda1ebef1dd5953ea1bcc562fb06b23e48ed34077fe32bb6d963","observation_id":"74faa652-0348-4b40-827f-ee2402e8c513","resolution":{"observed_at":"2026-08-11T12:47:49.179775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.158781Z","title":"Convergence analysis of prediction markets via randomized subspace descent.Advances in Neural Information Processing Systems, 28, 2015","venue":null,"work_id":"304902fb-cc57-45bf-b2cb-ff8a4359a40c","year":2015},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:47.993555Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:31f25f57c3dd048d9497799d959d92661047a67070f942a78a2e3f898102428f","observation_id":"b3a3fde2-e8d7-4e46-a381-721a2bdbe7f8","resolution":{"observed_at":"2026-08-11T12:47:49.164778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.142126Z","title":"Measuring sample quality with kernels","venue":null,"work_id":"08432830-f068-405e-8114-514e2bbaaf72","year":2017},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.000053Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:9dafc83d6ea66d7569d04cde184f97513f5b93402b4f96a02f9a51acfecbac45","observation_id":"da27c5a1-88ae-4992-8c01-c73e2d0b857e","resolution":{"observed_at":"2026-08-11T12:47:49.147307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.122854Z","title":"Rsn: randomized subspace Newton","venue":null,"work_id":"805e983c-e912-43e3-923c-9057b4d6df68","year":2019},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.004791Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:7bfdb8bc39b401d5eff1b37152738cbbdd6ce44b9ddca22b74bc75aacad0ea2e","observation_id":"39dc2350-dddf-4aff-931e-1702f598049c","resolution":{"observed_at":"2026-08-11T12:47:49.127658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.012264Z","title":"Randomized iterative methods for linear systems","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.012264Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:53368dde9f8a09c97743e1480f1ccdcbb8b97c04c8b10a368ecf88db77d14d0e","observation_id":"7eac7f1e-406b-4016-b1f8-1c6a5a1d573c","resolution":{"observed_at":"2026-08-11T12:47:48.012264Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.091534Z","title":"Stochastic quasi-gradient methods: Variance reduction via jacobian sketching.Mathematical Programming, 188 (1):135–192, 2021","venue":null,"work_id":"7e40a59b-93dc-4030-8394-db105490d8a6","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.016981Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:34eac313ae0a9472aa62d566f9b6ec4d2a64bbca4e2b174706b155d86918fc45","observation_id":"83395402-b65b-4688-82ad-ba9dfe4faaae","resolution":{"observed_at":"2026-08-11T12:47:49.097567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.06890","last_updated":"2016-01-28T06:43:52Z","snapshot_observed_at":"2026-08-14T22:17:30.313349Z","submitted_at":"2015-12-21T22:09:30Z","title":"Stochastic Dual Ascent for Solving Linear Systems","version":2},"cited_work":{"arxiv_id":"1512.06890","doi":null,"metadata_source":"pith","pith_arxiv_id":"1512.06890","snapshot_observed_at":"2026-08-11T12:47:48.354602Z","title":"Stochastic Dual Ascent for Solving Linear Systems","venue":"math.NA","work_id":"bdc0d598-ff80-4d45-a096-426bbe787f6b","year":2015},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.022086Z"},"links":{"cited_paper":"/paper/1512.06890","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:8c32afcf417cadd728359b3995774034102db7a8e03a62e9706a70e86bca56f9","observation_id":"60bb3cf2-2575-47c2-b465-b54469c7afa6","resolution":{"observed_at":"2026-08-11T12:47:48.361599Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.069725Z","title":"Improving neural network training in low dimensional random bases.Advances in Neural Information Processing Systems, 33:12140–12150, 2020","venue":null,"work_id":"504f0e3c-845d-47d4-8f18-2d799be80f57","year":2020},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.026812Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:cc4e5b708906e23fe293618367d7bf01534646798e6ab73e56098952a5ebb9c0","observation_id":"148cebe4-b818-4801-81e2-90c30d76cf82","resolution":{"observed_at":"2026-08-11T12:47:49.077756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.031900Z","title":"Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.031900Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:8d55f2f7866894182cc45799939681cc5d8efc6feee887deb11aa75c4277d0d7","observation_id":"b5d57527-ef78-4fe1-9839-3f368f492015","resolution":{"observed_at":"2026-08-11T12:47:48.031900Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.034645Z","title":"Sega: Variance reduction via gradient sketching.Advances in Neural Information Processing Systems, 31, 2018","venue":null,"work_id":"667cea7b-751f-40e4-b8c9-faf5776efcff","year":2018},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.039527Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:626643668fdfdc0afddc030ecb60c5ca12be57a6a6a86a842a9cfefa6053c063","observation_id":"91a4ef99-b684-4c5a-85e3-2f47d3fafc70","resolution":{"observed_at":"2026-08-11T12:47:49.044908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:49.014634Z","title":"Stochastic subspace cubic Newton method","venue":null,"work_id":"627c54b7-a455-40ca-b4ca-1d0fac910621","year":null},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.043800Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:7627a2688197f2732eb44fc42904b89df195f0b569eb45ce050a6004167da48f","observation_id":"c40f3ff2-42a9-41f9-a85a-b8cabc71a699","resolution":{"observed_at":"2026-08-11T12:47:49.023421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.048501Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.048501Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:43c9ed395778d27f680cc8221bc77aaca57529557dc547c7ad98e0d9e74f374a","observation_id":"1271388f-79e6-4225-94e2-c5d6acaee13f","resolution":{"observed_at":"2026-08-11T12:47:48.048501Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.974211Z","title":"Mirrored langevin dynamics","venue":null,"work_id":"9e3e01bc-a9c1-4e57-8dc2-77a41b911399","year":2018},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.053746Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:00ede0f02b2bdeac5a2e7aae0590ca0eaa49899738972961990e996ca34eb84a","observation_id":"af382f4c-2a3c-4a71-890e-58aac7acf207","resolution":{"observed_at":"2026-08-11T12:47:48.980117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.953553Z","title":"Communication-efficient distributed sgd with sketching","venue":null,"work_id":"ac087c91-e403-40d3-a1fd-4227e5180136","year":2019},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.059658Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:d277da3a1ee74355c0b184fa378d1ac53660ebc5c88542e61d9129364ee421b4","observation_id":"1e2f5a00-bc58-46d0-818c-a4ff1fb15a5b","resolution":{"observed_at":"2026-08-11T12:47:48.957929Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.937416Z","title":"On the relation between the sharpest directions of dnn loss and the sgd step length","venue":null,"work_id":"f222da88-e6fc-48b8-bff3-d28962231c4f","year":2019},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.062986Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:86af5f43c83f121c5be55771dd25b9eb997720369aa530b65845c45704cbd5df","observation_id":"49859dd0-2e35-4757-a6b4-513cdb4e8870","resolution":{"observed_at":"2026-08-11T12:47:48.942397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.922176Z","title":"Subspace diffusion generative models","venue":null,"work_id":"9e642a71-5dcc-4c69-89c5-ea2f39271b3b","year":null},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.067333Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:fcfc79f771331dd11e7367837a6db17d5e4401235d2f1d2a490c2e4d54f001b2","observation_id":"4f98377a-176b-4f15-b64e-f70cbd7b42e7","resolution":{"observed_at":"2026-08-11T12:47:48.928727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.904257Z","title":"Extensions of Lipschitz maps into Banach spaces","venue":null,"work_id":"d99f3d19-2e9c-46af-8e95-352474ea076d","year":1986},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.071933Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:db9faa5aae86dea9a12983861a4e31a21952de32bb887e6ceaed66d04a57d4c3","observation_id":"7fba6272-1782-4933-8171-daf27050ed46","resolution":{"observed_at":"2026-08-11T12:47:48.910716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.077419Z","title":"The variational formulation of the fokker–planck equation.SIAM journal on mathematical analysis, 29(1):1–17, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.077419Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:96b9a26aaac0d38d5b7bb86a891fe841a43899cbf2a762854224884f208d18ae","observation_id":"3953ad54-7f37-4742-9771-e2a89f7f0399","resolution":{"observed_at":"2026-08-11T12:47:48.077419Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.879330Z","title":"A stochastic subspace approach to gradient-free optimization in high dimensions","venue":null,"work_id":"cb6abcaa-0ab5-425a-a5c6-ebd95297a77b","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.082588Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:f65fca63fcde544fa93afc85ca54d4457e4daaf59fb89cea79f937d0e203122f","observation_id":"d5aaa1d2-8cb9-43c1-91b0-33af6a291c35","resolution":{"observed_at":"2026-08-11T12:47:48.885712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.087419Z","title":"Measuring the intrinsic dimension of objective landscapes","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.087419Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:17944a8ca49a2b7d042165301880125a11597fdebc467c6d8c734de505edb307","observation_id":"6e01b433-6813-4561-9094-0b39cd4a66d5","resolution":{"observed_at":"2026-08-11T12:47:48.087419Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.855148Z","title":"Low dimensional trajectory hypothesis is true: DNNs can be trained in tiny subspaces.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3):3411–3420, 2022","venue":null,"work_id":"55923046-59a8-46b4-8ed1-7722c378fcce","year":2022},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.092573Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:51dd9ca091661dc37358fdaffb46be9b8c9a07e55c5cc64b35dd1104ca676ba0","observation_id":"0ff4c4dc-783b-4212-b818-0e5ddb0bcdec","resolution":{"observed_at":"2026-08-11T12:47:48.859737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12857","last_updated":"2024-08-23T05:54:53Z","snapshot_observed_at":"2026-08-16T13:24:25.499799Z","submitted_at":"2024-08-23T05:54:53Z","title":"Memory-Efficient LLM Training with Online Subspace Descent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12857","snapshot_observed_at":"2026-08-11T12:47:48.096950Z","title":"Memory-efficient llm training with online subspace descent.arXiv preprint arXiv:2408.12857, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.096950Z"},"links":{"cited_paper":"/paper/2408.12857","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:b59d210948233661ee219a94a3e4ad98aaca44b7362a0993c11ec0c2de18a2bb","observation_id":"a8cfeba0-358d-4d64-b257-95b9e76c3c6a","resolution":{"observed_at":"2026-08-11T12:47:48.096950Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.840312Z","title":"Stein variational gradient descent: A general purpose Bayesian inference algorithm","venue":null,"work_id":"ee91783d-9fe7-4901-abb9-673ded33cdb5","year":2016},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.102103Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:8f4b82f139681ff29ad691b630da25d13029f5604b91fc39babed6cbbbdac2d5","observation_id":"33fa1c7b-6f61-4dc0-a1be-4bb908969e5d","resolution":{"observed_at":"2026-08-11T12:47:48.844648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.106281Z","title":"Relatively smooth convex optimization by first-order methods, and applications.SIAM Journal on Optimization, 28(1):333–354, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.106281Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:351c70e9fce63ccf3aece5b558ec897319ac28e88d39c79043073ba6ac2a788b","observation_id":"25197ec3-9298-43a2-afc1-4bdfd1ecad48","resolution":{"observed_at":"2026-08-11T12:47:48.106281Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.814292Z","title":"A complete recipe for stochastic gradient MCMC","venue":null,"work_id":"c89d1562-cf3e-4481-90c8-ce77a500ced0","year":2015},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.110809Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:375d58b670ecf7b9b16fb4add8e72d5b04cadfd1c8d5c01591e1e4a4fcaaf65c","observation_id":"5ccf4680-1478-4e01-8115-8755093c9d07","resolution":{"observed_at":"2026-08-11T12:47:48.819389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.797717Z","title":"Sampling in unit time with kernel fisher-rao flow","venue":null,"work_id":"dbb6b029-0c7f-4b7d-b881-8d1fd04e05ad","year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.115156Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:879e6abd63d800f21e9e5fd5d4348f11f1f954c8afeea0a7c447043eeb8093a0","observation_id":"9ce4135d-1625-42f5-b17f-8df9a427dac5","resolution":{"observed_at":"2026-08-11T12:47:48.802307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.774339Z","title":"McMahan and Matthew Streeter","venue":null,"work_id":"aefdb3a6-41e1-44cd-a53c-a965dcf66cc8","year":2010},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.119833Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:63c9d7ea8b2314e59dcd5cac4f6e5bc45cb9016b5d20f9b7bff14464a8de435a","observation_id":"93121d04-91ba-4724-97e2-ed5fe3f599cb","resolution":{"observed_at":"2026-08-11T12:47:48.778842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.124142Z","title":"Efficiency of coordinate descent methods on huge-scale optimization problems","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.124142Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:4e2c4ab0a68e91d33ea20c5f570a05effbbd5d3b8989c3e291e9b900712a5843","observation_id":"6e2f2045-91b0-4e76-9f2a-37e2e29f57a0","resolution":{"observed_at":"2026-08-11T12:47:48.124142Z","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":"2026-08-11T12:47:48.130316Z","title":"Random gradient-free minimization of convex functions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.130316Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:28af6b78696bf4d21fe392e2a00d6c942cd0a981c276f1a929e09b496221e64f","observation_id":"fc51b5c0-8511-4c9e-8135-96ae1bcd6e34","resolution":{"observed_at":"2026-08-11T12:47:48.130316Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.744622Z","title":"Lyapunov functions: An optimization theory perspective","venue":null,"work_id":"3b341d0c-b4d7-4b88-b3de-4a81633bb3b5","year":2017},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.136808Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:de47d4a67054dbd93c62f527a72c83423bd1d2c5f35418b89421dd20857b04f8","observation_id":"2c0503c0-fe07-4099-aa7a-91fdba5ed08b","resolution":{"observed_at":"2026-08-11T12:47:48.748684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.141422Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.141422Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:eb3c7bb551aee8e3ef9c91e9d70435c5706e8a6a5a973302c4f63de01b38b202","observation_id":"595b8926-531e-4d8e-aa7d-173ef3dc2b64","resolution":{"observed_at":"2026-08-11T12:47:48.141422Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.717716Z","title":"Stochastic zeroth-order discretizations of Langevin diffusions for Bayesian inference","venue":null,"work_id":"722486d9-4b34-43ee-a93a-2613e2f487e8","year":2022},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.145815Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:2065388d106cd66b77ecb138401bb45968e69c684a8b3c0ba0be9eca353bfabb","observation_id":"bb1a4f64-f1d7-4270-a078-4cda9142ac7e","resolution":{"observed_at":"2026-08-11T12:47:48.724845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07476","last_updated":"2017-10-05T13:28:50Z","snapshot_observed_at":"2026-08-14T21:29:08.308841Z","submitted_at":"2016-11-22T19:24:49Z","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07476","snapshot_observed_at":"2026-08-11T12:47:48.149756Z","title":"Eigenvalues of the hessian in deep learning: Singularity and beyond.arXiv preprint arXiv:1611.07476, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.149756Z"},"links":{"cited_paper":"/paper/1611.07476","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:3954c9d227b1cff5baf0b84ffd5c6257851c1a605363a745b5b5ebc1168e1ae0","observation_id":"b56649c8-1647-4fab-bfd6-53473b8b12a5","resolution":{"observed_at":"2026-08-11T12:47:48.149756Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.04454","last_updated":"2018-05-07T15:43:39Z","snapshot_observed_at":"2026-08-14T20:54:07.384012Z","submitted_at":"2017-06-14T12:50:00Z","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.04454","snapshot_observed_at":"2026-08-11T12:47:48.153955Z","title":"Empirical analysis of the hessian of over-parametrized neural networks.arXiv preprint arXiv:1706.04454, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.153955Z"},"links":{"cited_paper":"/paper/1706.04454","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:46931d21a0f8bf1284b8577d6b1d557dedd08eeae7489e0b2d86d0df667b3b64","observation_id":"3b9c5a5a-030a-4c6d-9ff6-755249ea3228","resolution":{"observed_at":"2026-08-11T12:47:48.153955Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.701397Z","title":"{Euclidean, metric, and Wasserstein } gradient flows: an overview","venue":null,"work_id":"a3b9207c-db72-4863-85a4-d0fe42a90c73","year":2017},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.157980Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:e601cd266b21a58c56b4e62285b443733612be7a5b9e5d8bb76448fd96b7b6d5","observation_id":"3a7b617e-5a95-4082-a17a-19469151a165","resolution":{"observed_at":"2026-08-11T12:47:48.707621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16002","last_updated":"2025-03-11T01:07:24Z","snapshot_observed_at":"2026-08-16T13:49:34.572593Z","submitted_at":"2024-05-25T01:44:35Z","title":"Does SGD really happen in tiny subspaces?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16002","snapshot_observed_at":"2026-08-11T12:47:48.161823Z","title":"Does sgd really happen in tiny subspaces? arXiv preprint arXiv:2405.16002, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.161823Z"},"links":{"cited_paper":"/paper/2405.16002","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:26f6cc9cdd335fc41d3701d21bf579d0763ad8cc22ddf804f9f9936a5f31ea08","observation_id":"b78413e4-9b2d-4fbd-8916-6bf3dd3d6e13","resolution":{"observed_at":"2026-08-11T12:47:48.161823Z","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":"2026-08-11T12:47:48.166250Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.166250Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:25802f563b471551560787c5c12c6cdd32057a77b520cbc3014ee5541068a011","observation_id":"fa5e5483-37d1-46b2-bd57-d5fd35abe9fe","resolution":{"observed_at":"2026-08-11T12:47:48.166250Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.669916Z","title":"Rmsprop: Divide the gradient by a running average of its recent magnitude.Coursera, 2012","venue":null,"work_id":"e25e060b-feb2-435a-ba08-aa56f2b79d3e","year":2012},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.170422Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:f9594df1e342dea3b6b10caad5313898ea5652e4d7f35fb2ece680c85a66baa2","observation_id":"f34beebf-4c94-42d1-8061-42c23638fdb0","resolution":{"observed_at":"2026-08-11T12:47:48.676051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.652766Z","title":"Optimal preconditioning and Fisher adaptive Langevin sampling","venue":null,"work_id":"e9429160-eb0c-444b-9f41-61e2f44dccd8","year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.174194Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:e1482600d2c49c31647016fd343646898e875955d7dc0f1bb22594b154f91b10","observation_id":"10c164f4-274f-49dc-9142-8d4b28ec7330","resolution":{"observed_at":"2026-08-11T12:47:48.659541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.639028Z","title":"Improved analysis of the subsampled randomized Hadamard transform","venue":null,"work_id":"896ed803-25aa-4289-8911-e50744e5bbce","year":2011},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.178073Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:c63cb76905f10bb7c629fd1fdb7d604f58ec2e9c1fefedd8f8fec0b00190e330","observation_id":"543e9ab6-7975-47d2-986a-cb8940b0ff79","resolution":{"observed_at":"2026-08-11T12:47:48.644400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T12:47:48.182145Z","title":"Theoretical guarantees for sampling and inference in generative models with latent diffusions","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.182145Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:f824012ebfa182aaee9e556471432ab9784c3b372650ba75205da55b74c9671b","observation_id":"1c476c60-59ff-4724-adc3-fdbdf812f1de","resolution":{"observed_at":"2026-08-11T12:47:48.182145Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.611689Z","title":"Score-basedgenerativemodelinginlatent space","venue":null,"work_id":"8693342c-0fec-452e-94c0-63d9f7a27fd4","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.187799Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:c58dd9ef3eaa37bc5a856004758fb2103cae4dbfb9e23714afbc0b96c6fb3554","observation_id":"b714cc63-3ff3-465a-ac0b-ceb7788178f1","resolution":{"observed_at":"2026-08-11T12:47:48.616248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.595641Z","title":"Optimal transport: old and new, volume 338","venue":null,"work_id":"c9eb3b65-2e3f-4bcf-8565-432fd611fa2d","year":2009},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.192867Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:a1829ce047a8c21aaf436947829d1fa173f1fc76ceb9e4482bbd34b07ea5492a","observation_id":"0e0ef4d9-b249-4330-8c7c-515a20dcf7ea","resolution":{"observed_at":"2026-08-11T12:47:48.600970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02426","last_updated":"2026-06-30T05:31:38Z","snapshot_observed_at":"2026-08-16T13:21:32.914993Z","submitted_at":"2024-09-04T04:14:02Z","title":"Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02426","snapshot_observed_at":"2026-08-11T12:47:48.197189Z","title":"Diffusion models learn low-dimensional distributions via subspace clustering","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.197189Z"},"links":{"cited_paper":"/paper/2409.02426","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:955a25c3c05f7013917dbf5a0fb0df1be54e5de43f6d51d6da29e56d4afe2d03","observation_id":"d1af4eeb-4a9b-4665-a29c-cbdffeb7c603","resolution":{"observed_at":"2026-08-11T12:47:48.197189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.04341","last_updated":"2020-08-05T01:28:44Z","snapshot_observed_at":"2026-07-06T08:50:09.743009Z","submitted_at":"2020-01-13T15:33:46Z","title":"Information Newton's flow: second-order optimization method in probability space","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.04341","snapshot_observed_at":"2026-08-11T12:47:48.201636Z","title":"Information Newton’s flow: second-order optimization method in probability space.arXiv preprint arXiv:2001.04341, 2020","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.201636Z"},"links":{"cited_paper":"/paper/2001.04341","citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:8b6217170a059f2658c42400434392c32fb83fef45880944d04e5845da627efb","observation_id":"6789308d-cc93-4197-bf6b-a496c2dda913","resolution":{"observed_at":"2026-08-11T12:47:48.201636Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.569837Z","title":"Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem","venue":null,"work_id":"07f68a13-8b03-461d-bfe4-16d24e25bdf8","year":2018},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.206193Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:fa675f120fdb099bc2bdb6860da9d027c0813c6a49986a43006076bf238802bd","observation_id":"cf6bada7-43a9-4f13-967f-73c5a8324662","resolution":{"observed_at":"2026-08-11T12:47:48.576109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.557005Z","title":"Coordinate descent algorithms.Mathematical programming, 151(1): 3–34, 2015","venue":null,"work_id":"6deeac3a-abdf-4550-b5d9-a9e946d4cb6e","year":2015},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.209979Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:d44d797b97905206b80550b7d30e6b40a975282366e2ce5c7b3f52fa7e76a434","observation_id":"fcbeda8d-71e0-4d01-8a57-8de9c7760d0d","resolution":{"observed_at":"2026-08-11T12:47:48.561884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.538848Z","title":"Scalablestochastic gradient Riemannian Langevin dynamics in non-diagonal metrics","venue":null,"work_id":"3e3e796f-15dd-43f3-9e6a-2212fc1acf13","year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.214520Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:3b62fca4a22ac7c4b965efa994911ca4db313ef99ff9fbb49b652f9ac821ca07","observation_id":"e10c696c-b746-4f93-a038-eec136a0a184","resolution":{"observed_at":"2026-08-11T12:47:48.543170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.523389Z","title":"Scalable semidefinite programming.SIAM Journal on Mathematics of Data Science, 3 (1):171–200, 2021","venue":null,"work_id":"ef1f1ade-35a1-4eb3-8398-61bba9c77f32","year":2021},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.219673Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:98070ce0ea775f9ea51b7c4ab57af066816b951bfcee1fe4f27e1402feb43ecd","observation_id":"f035b490-cc5b-4ee2-9383-cfdb4ea138b9","resolution":{"observed_at":"2026-08-11T12:47:48.527947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.510378Z","title":"Wasserstein control of mirror Langevin Monte Carlo","venue":null,"work_id":"ff915e1d-f9a7-4eb1-bf91-1c16737e900b","year":2020},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.223528Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:cfd3d89e4b74aa9d7a00e6a73ed53a0d65307fd0d0a62c9355cfd8e96d679f0c","observation_id":"858e9c3e-81b8-428d-a3a0-9bc953796d19","resolution":{"observed_at":"2026-08-11T12:47:48.514409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.493496Z","title":"Galore: memory-efficient llm training by gradient low-rank projection","venue":null,"work_id":"486db948-31e8-4323-bf32-eb4e853fe713","year":2024},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.228462Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:78c2bd44de08ba7d2faacaa42eded2d6d6d4eef7664b9b30c0e07002c234278b","observation_id":"e85d2c33-e7ee-47ef-a9fd-ba225e0fa31e","resolution":{"observed_at":"2026-08-11T12:47:48.501152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:47:48.477807Z","title":"25 Thus we can apply Grönwall’s lemma tof (Zs, Z′ s) to find f (Zt, Z′ t) ≤ exp(−2 Z t 0 mds)f (Z0, Z′ 0)","venue":null,"work_id":"8f727e9b-d64b-4053-9a43-5d6115384ae4","year":null},"citing_paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:48.232661Z"},"links":{"citing_paper":"/paper/2412.13928"},"observation_digest":"sha256:58c5bbb9a138c0921024b1ae153fc49eacf1a5dea893a00c34213bf2116cc33a","observation_id":"3c8766a2-16fe-4334-99ed-1eb9786f4881","resolution":{"observed_at":"2026-08-11T12:47:48.483105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.13928","last_updated":"2025-05-19T18:37:05Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-16T03:03:09.222396Z","submitted_at":"2024-12-18T15:12:41Z","title":"Subspace Langevin Monte Carlo"},"reference_resolution":{"displayed":75,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":1,"verified_fuzzy":49},"total_outbound_references":75},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 0 inbound Pith citation observations for arXiv:2412.13928."}