{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GJVJ2WLHW67ELHNGQQCCXRUWVD","short_pith_number":"pith:GJVJ2WLH","schema_version":"1.0","canonical_sha256":"326a9d5967b7be459da684042bc696a8d6cff3358b5f223678ef570694304acb","source":{"kind":"arxiv","id":"2409.14989","version":2},"attestation_state":"computed","paper":{"title":"Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alen Aliev, Eduard Gorbunov, Martin Tak\\'a\\v{c}, Nazarii Tupitsa, Peter Richt\\'arik, Samuel Horv\\'ath, Sayantan Choudhury","submitted_at":"2024-09-23T13:11:37Z","abstract_excerpt":"Due to the non-smoothness of optimization problems in Machine Learning, generalized smoothness assumptions have been gaining a lot of attention in recent years. One of the most popular assumptions of this type is $(L_0,L_1)$-smoothness (Zhang et al., 2020). In this paper, we focus on the class of (strongly) convex $(L_0,L_1)$-smooth functions and derive new convergence guarantees for several existing methods. In particular, we derive improved convergence rates for Gradient Descent with (Smoothed) Gradient Clipping and for Gradient Descent with Polyak Stepsizes. In contrast to the existing resu"},"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":"2409.14989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-09-23T13:11:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1792269da7094b3a993bd34354ca61f473f05a89632ead336f21f92e835b717","abstract_canon_sha256":"f8b69cea7e98c0817e7218bafdcd3fb8473a9bc69ea0e4c3115e6eb657ac28c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:04.512532Z","signature_b64":"pvK2Lx9d9jV5gO6eI/GXy3Lll/0eHFAkf/cU/Hml54hZZhMOMjyvZDkMzBrfQo4UQ7RUfAJ1SgboAJiQEyGsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"326a9d5967b7be459da684042bc696a8d6cff3358b5f223678ef570694304acb","last_reissued_at":"2026-07-05T09:54:04.512061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:04.512061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alen Aliev, Eduard Gorbunov, Martin Tak\\'a\\v{c}, Nazarii Tupitsa, Peter Richt\\'arik, Samuel Horv\\'ath, Sayantan Choudhury","submitted_at":"2024-09-23T13:11:37Z","abstract_excerpt":"Due to the non-smoothness of optimization problems in Machine Learning, generalized smoothness assumptions have been gaining a lot of attention in recent years. One of the most popular assumptions of this type is $(L_0,L_1)$-smoothness (Zhang et al., 2020). In this paper, we focus on the class of (strongly) convex $(L_0,L_1)$-smooth functions and derive new convergence guarantees for several existing methods. In particular, we derive improved convergence rates for Gradient Descent with (Smoothed) Gradient Clipping and for Gradient Descent with Polyak Stepsizes. In contrast to the existing resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14989","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/2409.14989/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":"2409.14989","created_at":"2026-07-05T09:54:04.512121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14989v2","created_at":"2026-07-05T09:54:04.512121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14989","created_at":"2026-07-05T09:54:04.512121+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJVJ2WLHW67E","created_at":"2026-07-05T09:54:04.512121+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJVJ2WLHW67ELHNG","created_at":"2026-07-05T09:54:04.512121+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJVJ2WLH","created_at":"2026-07-05T09:54:04.512121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.16468","citing_title":"Frank-Wolfe Algorithms for (L0, L1)-smooth functions","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15522","citing_title":"Stochastic Non-Smooth Convex Optimization with Unbounded Gradients","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16468","citing_title":"Frank-Wolfe Algorithms for (L0, L1)-smooth functions","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD","json":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD.json","graph_json":"https://pith.science/api/pith-number/GJVJ2WLHW67ELHNGQQCCXRUWVD/graph.json","events_json":"https://pith.science/api/pith-number/GJVJ2WLHW67ELHNGQQCCXRUWVD/events.json","paper":"https://pith.science/paper/GJVJ2WLH"},"agent_actions":{"view_html":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD","download_json":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD.json","view_paper":"https://pith.science/paper/GJVJ2WLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14989&json=true","fetch_graph":"https://pith.science/api/pith-number/GJVJ2WLHW67ELHNGQQCCXRUWVD/graph.json","fetch_events":"https://pith.science/api/pith-number/GJVJ2WLHW67ELHNGQQCCXRUWVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD/action/storage_attestation","attest_author":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD/action/author_attestation","sign_citation":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD/action/citation_signature","submit_replication":"https://pith.science/pith/GJVJ2WLHW67ELHNGQQCCXRUWVD/action/replication_record"}},"created_at":"2026-07-05T09:54:04.512121+00:00","updated_at":"2026-07-05T09:54:04.512121+00:00"}