{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HKPP6SNU7LUPDNXZ2FVNSLBOYS","short_pith_number":"pith:HKPP6SNU","schema_version":"1.0","canonical_sha256":"3a9eff49b4fae8f1b6f9d16ad92c2ec4a93de7b524eeeece4ab63cad25e03712","source":{"kind":"arxiv","id":"2311.13877","version":1},"attestation_state":"computed","paper":{"title":"Locally Optimal Descent for Dynamic Stepsize Scheduling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Cohen, Amit Daniely, Gilad Yehudai, Mariano Schain, Tomer Koren, Yoel Drori","submitted_at":"2023-11-23T09:57:35Z","abstract_excerpt":"We introduce a novel dynamic learning-rate scheduling scheme grounded in theory with the goal of simplifying the manual and time-consuming tuning of schedules in practice. Our approach is based on estimating the locally-optimal stepsize, guaranteeing maximal descent in the direction of the stochastic gradient of the current step. We first establish theoretical convergence bounds for our method within the context of smooth non-convex stochastic optimization, matching state-of-the-art bounds while only assuming knowledge of the smoothness parameter. We then present a practical implementation of "},"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":"2311.13877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T09:57:35Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a38d7c6d14a21a1aba7c053e92afd3a4a934014f4892a37fa8b624cf188947e8","abstract_canon_sha256":"53cd33e86f468ba58dfcfdb8c8cf097a06bebb85eb9c5d10592a2c6eb008e858"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:09.510823Z","signature_b64":"bZMSBzX3hUr6slBsR+TnbdIiFHrZXc9U9f5Q+ucTX1NF7q4v155gLKkG9qyZcZRzZCxDqk8nxhymB7dQs1hnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a9eff49b4fae8f1b6f9d16ad92c2ec4a93de7b524eeeece4ab63cad25e03712","last_reissued_at":"2026-07-05T07:16:09.510228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:09.510228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locally Optimal Descent for Dynamic Stepsize Scheduling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Cohen, Amit Daniely, Gilad Yehudai, Mariano Schain, Tomer Koren, Yoel Drori","submitted_at":"2023-11-23T09:57:35Z","abstract_excerpt":"We introduce a novel dynamic learning-rate scheduling scheme grounded in theory with the goal of simplifying the manual and time-consuming tuning of schedules in practice. Our approach is based on estimating the locally-optimal stepsize, guaranteeing maximal descent in the direction of the stochastic gradient of the current step. We first establish theoretical convergence bounds for our method within the context of smooth non-convex stochastic optimization, matching state-of-the-art bounds while only assuming knowledge of the smoothness parameter. We then present a practical implementation of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13877","kind":"arxiv","version":1},"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/2311.13877/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":"2311.13877","created_at":"2026-07-05T07:16:09.510296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13877v1","created_at":"2026-07-05T07:16:09.510296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13877","created_at":"2026-07-05T07:16:09.510296+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKPP6SNU7LUP","created_at":"2026-07-05T07:16:09.510296+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKPP6SNU7LUPDNXZ","created_at":"2026-07-05T07:16:09.510296+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKPP6SNU","created_at":"2026-07-05T07:16:09.510296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS","json":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS.json","graph_json":"https://pith.science/api/pith-number/HKPP6SNU7LUPDNXZ2FVNSLBOYS/graph.json","events_json":"https://pith.science/api/pith-number/HKPP6SNU7LUPDNXZ2FVNSLBOYS/events.json","paper":"https://pith.science/paper/HKPP6SNU"},"agent_actions":{"view_html":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS","download_json":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS.json","view_paper":"https://pith.science/paper/HKPP6SNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13877&json=true","fetch_graph":"https://pith.science/api/pith-number/HKPP6SNU7LUPDNXZ2FVNSLBOYS/graph.json","fetch_events":"https://pith.science/api/pith-number/HKPP6SNU7LUPDNXZ2FVNSLBOYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS/action/storage_attestation","attest_author":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS/action/author_attestation","sign_citation":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS/action/citation_signature","submit_replication":"https://pith.science/pith/HKPP6SNU7LUPDNXZ2FVNSLBOYS/action/replication_record"}},"created_at":"2026-07-05T07:16:09.510296+00:00","updated_at":"2026-07-05T07:16:09.510296+00:00"}