{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3R3BOGUBAO46SNWDTMPP7TID44","short_pith_number":"pith:3R3BOGUB","schema_version":"1.0","canonical_sha256":"dc76171a8103b9e936c39b1effcd03e72b9bdc0abd174d6725715238f67f898a","source":{"kind":"arxiv","id":"2412.17050","version":2},"attestation_state":"computed","paper":{"title":"Linear Convergence Rate in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Aleksandr Lobanov, Alexander Gasnikov, Eduard Gorbunov, Martin Tak\\'a\\v{c}","submitted_at":"2024-12-22T15:00:32Z","abstract_excerpt":"The gradient descent (GD) method -- is a fundamental and likely the most popular optimization algorithm in machine learning (ML), with a history traced back to a paper in 1847 (Cauchy, 1847). It was studied under various assumptions, including so-called $(L_0,L_1)$-smoothness, which received noticeable attention in the ML community recently. In this paper, we provide a refined convergence analysis of gradient descent and its variants, assuming generalized smoothness. In particular, we show that $(L_0,L_1)$-GD has the following behavior in the convex setup: as long as $\\|\\nabla f(x^k)\\| \\geq \\f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.17050","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-22T15:00:32Z","cross_cats_sorted":[],"title_canon_sha256":"fd883f88392cfb2293de2569c6b937421008147628d0f2fa8ac3e62161fdc80e","abstract_canon_sha256":"5c37cd375bc3eb22132687129987b69c0d1955f0db1f2b99aacc52599b216dfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:40.373877Z","signature_b64":"R+unk+IcNBmYVAfTKXCXIBv5T6vOMJESqtMEDovaxbjvc0Lxul6+5hO5R/YZ4YSEePYaXJyM2Mut4qWwjJvHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc76171a8103b9e936c39b1effcd03e72b9bdc0abd174d6725715238f67f898a","last_reissued_at":"2026-07-05T10:16:40.373326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:40.373326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Convergence Rate in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Aleksandr Lobanov, Alexander Gasnikov, Eduard Gorbunov, Martin Tak\\'a\\v{c}","submitted_at":"2024-12-22T15:00:32Z","abstract_excerpt":"The gradient descent (GD) method -- is a fundamental and likely the most popular optimization algorithm in machine learning (ML), with a history traced back to a paper in 1847 (Cauchy, 1847). It was studied under various assumptions, including so-called $(L_0,L_1)$-smoothness, which received noticeable attention in the ML community recently. In this paper, we provide a refined convergence analysis of gradient descent and its variants, assuming generalized smoothness. In particular, we show that $(L_0,L_1)$-GD has the following behavior in the convex setup: as long as $\\|\\nabla f(x^k)\\| \\geq \\f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17050","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.17050/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.17050","created_at":"2026-07-05T10:16:40.373390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17050v2","created_at":"2026-07-05T10:16:40.373390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17050","created_at":"2026-07-05T10:16:40.373390+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R3BOGUBAO46","created_at":"2026-07-05T10:16:40.373390+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R3BOGUBAO46SNWD","created_at":"2026-07-05T10:16:40.373390+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R3BOGUB","created_at":"2026-07-05T10:16:40.373390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14800","citing_title":"Avoiding Bias in Clipped SGD for Overparameterized Models under Generalized Smoothness","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44","json":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44.json","graph_json":"https://pith.science/api/pith-number/3R3BOGUBAO46SNWDTMPP7TID44/graph.json","events_json":"https://pith.science/api/pith-number/3R3BOGUBAO46SNWDTMPP7TID44/events.json","paper":"https://pith.science/paper/3R3BOGUB"},"agent_actions":{"view_html":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44","download_json":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44.json","view_paper":"https://pith.science/paper/3R3BOGUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17050&json=true","fetch_graph":"https://pith.science/api/pith-number/3R3BOGUBAO46SNWDTMPP7TID44/graph.json","fetch_events":"https://pith.science/api/pith-number/3R3BOGUBAO46SNWDTMPP7TID44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44/action/storage_attestation","attest_author":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44/action/author_attestation","sign_citation":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44/action/citation_signature","submit_replication":"https://pith.science/pith/3R3BOGUBAO46SNWDTMPP7TID44/action/replication_record"}},"created_at":"2026-07-05T10:16:40.373390+00:00","updated_at":"2026-07-05T10:16:40.373390+00:00"}