{"as_of":"2026-08-16T18:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:02a9d62bbfb7e55417fbbb5214b05784214a812e7a5a533991f1ad841e0ba5d9","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:30:25.152781Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:18:52.031537Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-15T16:18:52.617155Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"cited_work":{"arxiv_id":"2505.04599","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.04599","snapshot_observed_at":"2026-08-15T16:18:52.617155Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","venue":"cs.LG","work_id":"d8994d06-4268-40dd-abd2-5a4eff591502","year":2025},"citing_paper":{"arxiv_id":"2509.08726","last_updated":"2026-06-01T18:00:38Z","snapshot_observed_at":"2026-08-15T15:58:32.667704Z","submitted_at":"2025-09-10T16:17:19Z","title":"Decentralized Stochastic Nonconvex Optimization under the $(L_0,L_1)$-Smoothness","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:52.031537Z"},"links":{"cited_paper":"/paper/2505.04599","citing_paper":"/paper/2509.08726"},"observation_digest":"sha256:c372b063c3f261c9f03df5b0e3a5f86511fa7ee2e5a86fd7027c72ac7862d436","observation_id":"3e89b0cd-e87f-4110-b37e-38e86be44b1a","resolution":{"observed_at":"2026-08-15T16:18:52.623130Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2505.04599/citation-record","integrity":"/paper/2505.04599/integrity","json":"/paper/2505.04599/citation-record.json","paper":"/paper/2505.04599"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:30:25.766918Z","title":null,"venue":null,"work_id":"d830b1b2-0f89-46d7-bde3-d37b880c37bb","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.003896Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:c97a547c135af11e87dd09b52f6f84e8d649e5dc7bb4317e40b8e4558ebe04e5","observation_id":"a2694726-8f38-48c1-b075-4263af3617fb","resolution":{"observed_at":"2026-08-15T23:30:25.769951Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.718790Z","title":"Therefore, the effective learning rate of the algorithm at stept is ηt = η √ γ2 +∑ t−1 i=0 ‖F (xi,ξi)‖2 = η√ γ2 +t(ǫ2 +σ2) =αt+2","venue":null,"work_id":"6d16c508-fa1c-48c1-851e-17ca4a7295bd","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.022847Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:0473e80e3c2763f1a96cf2d6625a0c0accc94650a80fec438b77df9468ed364c","observation_id":"f1d6d86c-4b02-4429-b2b8-f7f311c05e42","resolution":{"observed_at":"2026-08-15T23:30:25.722252Z","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":"2026-08-15T23:30:25.507168Z","title":"We now bound the remaining constants","venue":null,"work_id":"92b9b5cf-7c7e-446f-bba2-09d95f40754f","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.100485Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:a4db12464ea7166b7f1d198146fcbb0423ba8c52e66949d9db3718e0e72d2d4a","observation_id":"f71e23ea-10e6-4706-ac5e-30ff33ab47a8","resolution":{"observed_at":"2026-08-15T23:30:25.510513Z","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":"2026-08-15T23:30:25.652720Z","title":null,"venue":null,"work_id":"12abe571-88b3-41e8-9100-a0ac62c0838d","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.048018Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:887a4e8c675d2c6356180df184652466101e3091e008e65b5a522fa23a04cb48","observation_id":"162b8764-b904-4214-ab15-703b480c2980","resolution":{"observed_at":"2026-08-15T23:30:25.656138Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.684474Z","title":"Let algorithmADAN denote Decorrelated AdaGrad-Norm with parameters η >0 and 0<γ ≤ ∆ L1 8 log ( 1 + 48 ∆ L2 1 L0 )","venue":null,"work_id":"ef1f5210-86cd-4506-b6f0-b42f0fada7f0","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.034340Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:87f4dd61e22faf9ab5257a7fb01c78c45947d385344a976cc27c53f713da650a","observation_id":"5f2d3f58-2eb0-4417-b339-cf729753f331","resolution":{"observed_at":"2026-08-15T23:30:25.688372Z","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":"2026-08-15T23:30:24.976572Z","title":"Near -optimal non-convex stochastic opti- mization under generalized smoothness","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:24.976572Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:295c5a7a0cd4d1b93bcf939ccd83d651ef634295f7c1b8ecb71fcfff9c15bc8f","observation_id":"05d82fd6-c6b7-4986-abb3-0b577140bb86","resolution":{"observed_at":"2026-08-15T23:30:24.976572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1002.4908","last_updated":"2010-07-07T19:07:16Z","snapshot_observed_at":"2026-08-15T05:25:29.252288Z","submitted_at":"2010-02-26T01:36:34Z","title":"Adaptive Bound Optimization for Online Convex Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1002.4908","snapshot_observed_at":"2026-08-15T23:30:24.980118Z","title":"Adaptive bound opti mization for online convex opti- mization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:24.980118Z"},"links":{"cited_paper":"/paper/1002.4908","citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:92a106c7bd26f1a9dbf3dbf9ef0c5ecd1bed1af3c9ad52515bb68da74fe3d9de","observation_id":"fad08475-e6ef-4ba2-9812-fe6e7d8c2154","resolution":{"observed_at":"2026-08-15T23:30:24.980118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.00883","last_updated":"2023-06-02T23:35:16Z","snapshot_observed_at":"2026-08-16T15:51:33.023197Z","submitted_at":"2023-03-02T00:57:38Z","title":"Variance-reduced Clipping for Non-convex Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.00883","snapshot_observed_at":"2026-08-15T23:30:24.984392Z","title":"V ariance-reduced clipping for non-convex optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:24.984392Z"},"links":{"cited_paper":"/paper/2303.00883","citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:d616c01034def38a94824fb7c59a4c2baadac7cbdf595dbc965cdd4a382c63cd","observation_id":"70402f0a-9d47-4096-b2f3-c8db8dc97d71","resolution":{"observed_at":"2026-08-15T23:30:24.984392Z","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":"2026-08-15T23:30:25.785960Z","title":"Adagrad stepsizes: Sharp convergence over nonconvex landscapes","venue":null,"work_id":"c18dc16a-c987-468a-be6d-2ea9ace02fa0","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:24.988099Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:c41084103ed9fcea2840b89854032cb1d43b877f14bf1a7415a580aacb2ecc84","observation_id":"fc002a4f-2e9b-478e-b4d3-98062730549d","resolution":{"observed_at":"2026-08-15T23:30:25.789540Z","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":"2026-08-15T23:30:25.552411Z","title":"Suppose g ∈ Rd with ‖g‖ =ǫ","venue":null,"work_id":"ac6575a3-cb62-41b8-a510-4032243d0c6c","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.085428Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:cbf85d5266481fee3f2519ddc1efbb4b2968f85e89d59dda5ba9f98bd06a978b","observation_id":"cdd59b75-7938-48fb-92d4-ce03865715d6","resolution":{"observed_at":"2026-08-15T23:30:25.555925Z","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":"2026-08-15T23:30:25.408279Z","title":null,"venue":null,"work_id":"6502594a-b683-40dc-82d4-6ae398aa9cf5","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.134599Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:dc06e373c6f4031b17a934860a173814cf49348d59bce0f7cee6903f68160945","observation_id":"4bfd7057-a46e-485e-8197-b0daceca7bb4","resolution":{"observed_at":"2026-08-15T23:30:25.412347Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.757298Z","title":"(8) 15 Published as a conference paper at ICLR 2025 The RHS of Equation 7 can be bounded as 4 L1 log ( 1 + L1gt+1 L0 ) = 4 L1 log ( 1 + ∆ L2 1 L0 ( 576(t +","venue":null,"work_id":"278182e2-0aa0-4b4e-a657-059196d830dc","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.008158Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:df7e785a4faa0c005933c55375f29f931e5ffb8a450c4b54f0d1b6cfbdf5e8eb","observation_id":"41c979b7-8086-4eeb-a316-0491e8f52aac","resolution":{"observed_at":"2026-08-15T23:30:25.760537Z","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":"2026-08-15T23:30:25.747827Z","title":"f is informally pictured in Figure 1b of the main text","venue":null,"work_id":"897cea33-db6c-4d85-8526-cf03ff71809b","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.011864Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:e51f7bdf1a3279b5f420974c05f7cb12289d89ce8655d7bf61a244e2f815998a","observation_id":"81248594-5734-4c61-8ff6-21b98f444777","resolution":{"observed_at":"2026-08-15T23:30:25.750835Z","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":"2026-08-15T23:30:25.738349Z","title":"Thereforef (x0) − infxf (x) ≤ ∆","venue":null,"work_id":"1ca3e38c-591f-43d1-b446-752ce6765e48","year":2020},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.015426Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:a87cb4ac9352d8f43d6e37cbb0ec0f985797623e727650f25fd9ef9b785261f1","observation_id":"03ce0f66-4c72-4d0f-b28c-2ef8ae9bc01c","resolution":{"observed_at":"2026-08-15T23:30:25.741400Z","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":"2026-08-15T23:30:25.729212Z","title":null,"venue":null,"work_id":"f90ff14c-00bb-4de2-b951-a6a6b49096e5","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.019334Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:04783692e9c66bcd0bf37bafc997db50d6a40bba54acf7515882b175b152046f","observation_id":"51b42532-16df-4479-9363-b0ce55b2b23a","resolution":{"observed_at":"2026-08-15T23:30:25.732272Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.707281Z","title":"Actually,f does not satisfy this condition becausef is not even lower bounded, due to the linear term ǫ⟨x, e1⟩","venue":null,"work_id":"c3d68a05-270a-4c78-bdab-7ca7cacb6998","year":2020},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.026471Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:de2afaef5ff8b8d8c4acca15f0c01581a4faf5796afb82ac525c1fed2fe67bb0","observation_id":"0dd5b158-8ee9-4016-80d8-dc3d403b0b16","resolution":{"observed_at":"2026-08-15T23:30:25.711410Z","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":"2026-08-15T23:30:25.695336Z","title":"Specifically, we need ˆf which is lower bounded and that satisfies: ∇ ˆf (xt) = ∇f (xt), ˆf (xt) = f (xt) for all 0 ≤t ≤T","venue":null,"work_id":"d8c6eb3e-e68b-4a23-a48f-7009480ca9a4","year":2020},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.030305Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:85c24259679c9784a80c31f758056ee2056fca52f87dc9ed245ac1790aed7dde","observation_id":"28da9ef0-af29-4dc3-839e-92775aa0863f","resolution":{"observed_at":"2026-08-15T23:30:25.699836Z","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":"2026-08-15T23:30:25.674157Z","title":"First, recall the definition of ψ: ˜ψ(x) = L0 L2 1 (exp (L1|x|) −L1|x| − 1)","venue":null,"work_id":"9b3ee8f2-7bc3-43da-b94c-5f161bbd592a","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.038819Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:67148669c329c554eb7b1d5803391fbcbc6a751d785ae29c08e2d0259b7465d1","observation_id":"a0e8882c-eeb2-4dd2-a9ff-16b102a903de","resolution":{"observed_at":"2026-08-15T23:30:25.677814Z","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":"2026-08-15T23:30:25.663084Z","title":null,"venue":null,"work_id":"2095015b-2141-474c-bcfd-768331e81c0c","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.043439Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:7e6be676df01a0087d8a6d967d715484b7f8145417e7fc1a40703b4c9c6414a9","observation_id":"e3562ffb-1431-458e-b79b-44c8185ca0ba","resolution":{"observed_at":"2026-08-15T23:30:25.666623Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.641913Z","title":"Therefore, with the initial point x0 =m + ∆ 2ǫ , the objective satisfies f (x0) − inf x f (x) = ǫ(x0 −m) +ψ(m) =ǫ ∆ 2ǫ + ∆ 2 = ∆","venue":null,"work_id":"e38319cd-cbd0-435b-9f8c-26f8a45fea5b","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.052827Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:6efb6373095444c06d7bae075681b268d57ae525623e7a157a2603b030346d4d","observation_id":"7cdca7ed-d1b5-49ec-a00b-119708470b12","resolution":{"observed_at":"2026-08-15T23:30:25.645814Z","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":"2026-08-15T23:30:25.630494Z","title":"If η ≥ √ 2γ L1σ log ( 1 + L1ǫ L0 ) , then by Lemma 3 there exists a problem instance for which Dec orrelated AdaGrad will never find an ǫ-approximate stationary point","venue":null,"work_id":"f8cab4df-4b99-4d63-845f-78a59529e143","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.056816Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:54368cb2ae56e73333d23c183c905a5486c6ab8b0ba733ba8371b2e13c9cdd9e","observation_id":"b84d0707-bf2e-4b9c-9461-5f94a4638b98","resolution":{"observed_at":"2026-08-15T23:30:25.634333Z","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":"2026-08-15T23:30:25.619842Z","title":null,"venue":null,"work_id":"06adae98-5860-4c1b-a436-0a80fcd62c2f","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.061332Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:b6767e35855ddc5dfddd5df464b41fcf88e2d17d9ef207fd692527d8c91e46a3","observation_id":"297f349c-c3b1-4764-b5e4-2ad024615f47","resolution":{"observed_at":"2026-08-15T23:30:25.623723Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.608263Z","title":"Recall the function ψ : R → R defined as ψ(x) = L0 L2 1 (exp(L1|x|) −L1|x| − 1)","venue":null,"work_id":"b1357dad-64e4-49e3-bd0b-d0cb75645caa","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.065780Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:e4e65d4ad7434c3681f309dfeccde6a38769ad018b7928eba1753e9b48f3d374","observation_id":"7d83cb05-b831-4ea8-b494-0dea2b7ec6cc","resolution":{"observed_at":"2026-08-15T23:30:25.612319Z","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":"2026-08-15T23:30:25.596932Z","title":"In this case, the learning rate α(g) is large enough to ensure that f (xt+1) ≥ f (xt) for an exponentially increasing f","venue":null,"work_id":"25f05b97-c6a9-42fa-be34-87f7d95e6b7f","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.069732Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:4c7f6e88d30d83115e82eb08c9926ed39b8ea26042da084d5cc1eb66b8cc4962","observation_id":"8e5ee1b8-2362-45e8-9dc0-d76e99a1a971","resolution":{"observed_at":"2026-08-15T23:30:25.600941Z","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":"2026-08-15T23:30:25.586248Z","title":"This completes the induction","venue":null,"work_id":"35e5abec-c176-4232-99d2-3ced63ab08c7","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.073300Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:ad6416ecfeb06056c55d18933d2c3209e9c472cb09810c7ae3462f2c41f8a8d4","observation_id":"04a1310b-39c7-43ed-b626-2dc68e25eca2","resolution":{"observed_at":"2026-08-15T23:30:25.589932Z","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":"2026-08-15T23:30:25.574387Z","title":"Also, ‖g1 −ℓg‖ = |c1 −ℓ|‖g‖ =ℓ −c1 = 1 −p p (c2 −ℓ) ≤ 1 −p p (σ1 +σ2ℓ) ≤σ1 +σ2ℓ, where the last inequality uses p > 1 2","venue":null,"work_id":"12b32962-78ce-476f-9a23-5c4a63e1feb3","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.076934Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:ad9a45701b60fdc300a6eecbb2b3a36d599f0b3ad64b4c3917a715d83ae691df","observation_id":"3cc4a260-40a6-410a-ba46-11495783b782","resolution":{"observed_at":"2026-08-15T23:30:25.578621Z","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":"2026-08-15T23:30:25.539722Z","title":"The upper bound of ‖yi‖ in the definition of k1 ensures that Equation 31 is satisfied","venue":null,"work_id":"0b678c07-feb2-4e8f-8570-dc09b0fa44e4","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.089355Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:8f0a7ec65aaf3021777cfcfa28313eded9a852e92aa50e6aee41d583d23e0b9e","observation_id":"8edbb6e2-a660-464a-b4a4-dcee4a7d6676","resolution":{"observed_at":"2026-08-15T23:30:25.543601Z","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":"2026-08-15T23:30:25.528987Z","title":null,"venue":null,"work_id":"70c394a9-e00d-49ad-b248-ebff0a813186","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.092804Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:6178f7f4682da543dbc775eb10f64d537df64e3f65793670dc045ea7636ee84a","observation_id":"7251ec45-044a-4a1d-8e24-8563c5db5e59","resolution":{"observed_at":"2026-08-15T23:30:25.532573Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.517526Z","title":"We can also bound β(yk1 ) using the assumed condition α(g) < 4m |g| , since we previously showed that (yk1, yk+1) satisfies Equation 29 through Equation","venue":null,"work_id":"b73ca2f6-a168-4e06-9a65-1e3baa0915c6","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.096643Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:85f1430ca9eafa6ab024e3052b70150994ffbe7673475686e4a2853c9591cd07","observation_id":"61092573-2b38-42db-acf3-14e22a087e98","resolution":{"observed_at":"2026-08-15T23:30:25.521966Z","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":"2026-08-15T23:30:25.497064Z","title":null,"venue":null,"work_id":"84c49da3-54a8-4fd5-8348-9b3437d8526f","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.105179Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:d603b8109b3116261132e6f66c56410bbf60e95e928826baedd7cb06b43cbab0","observation_id":"56975a94-a671-43bf-ba50-5c8f4124e53f","resolution":{"observed_at":"2026-08-15T23:30:25.500610Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.486460Z","title":"For b1: b1 = 1−p1 p1 ( σ1 + ( σ2 − p1 1−p1 ) G ) ((σ2 + 1)(2p1 −","venue":null,"work_id":"4569819a-2c8f-4f12-aea5-6af0f731ed9c","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.108940Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:463155cac42d36f051dd43db5117d7b4a5d0d564464e6da07fd0ced605d80ade","observation_id":"5fefb382-468e-4d51-b788-190b62a21471","resolution":{"observed_at":"2026-08-15T23:30:25.489870Z","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":"2026-08-15T23:30:25.562554Z","title":"Also as in the first case, |c1 −ℓ| ≤ |c2 −ℓ|","venue":null,"work_id":"60ade312-102e-4e55-ba4a-ddc93a719983","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.080939Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:2d2f452f88f294da573f6839d85253ec53631c71f4fd0865d6162e0f52dd4c14","observation_id":"2ea15521-7d9a-4e13-95af-0e7976cf6cb1","resolution":{"observed_at":"2026-08-15T23:30:25.566506Z","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":"2026-08-15T23:30:25.476157Z","title":null,"venue":null,"work_id":"995035c7-8134-4076-bfa4-21e92bbeda3e","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.112351Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:108e35e3213532057690e06ac2f0a7645a6254a6f07879a8e27ecb680491e49a","observation_id":"687c049a-651f-4bb9-8677-b92c85d43cbc","resolution":{"observed_at":"2026-08-15T23:30:25.479666Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T23:30:25.465534Z","title":"42 Published as a conference paper at ICLR 2025 Proof","venue":null,"work_id":"63af3a6c-5933-4933-90a1-89912a3abfac","year":2025},"citing_paper":{"arxiv_id":"2505.04599","last_updated":"2025-05-07T17:40:12Z","snapshot_observed_at":"2026-08-15T23:22:22.009037Z","submitted_at":"2025-05-07T17:40:12Z","title":"Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T23:30:25.116307Z"},"links":{"citing_paper":"/paper/2505.04599"},"observation_digest":"sha256:44a0afa32bffd4dc29f933123a78829e934a90743efe897d8cbec3932a70646a","observation_id":"5464baa6-62bf-43ff-ad3a-5ba9bc4cd8f8","resolution":{"observed_at":"2026-08-15T23:30:25.469142Z","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":"2026-08-15T23:30:25.452977Z","title":"Therefore,t ≤ ∆ 2α(ǫ)ǫ2 implies thatt