{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CQXY5XWRXK2ECKXCCMBI5DHZXC","short_pith_number":"pith:CQXY5XWR","schema_version":"1.0","canonical_sha256":"142f8eded1bab4412ae213028e8cf9b8a1eec490689e0e25dcef86eab94f983d","source":{"kind":"arxiv","id":"2406.04142","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Dimitris Oikonomou, Nicolas Loizou","submitted_at":"2024-06-06T15:08:06Z","abstract_excerpt":"Stochastic gradient descent with momentum, also known as Stochastic Heavy Ball method (SHB), is one of the most popular algorithms for solving large-scale stochastic optimization problems in various machine learning tasks. In practical scenarios, tuning the step-size and momentum parameters of the method is a prohibitively expensive and time-consuming process. In this work, inspired by the recent advantages of stochastic Polyak step-size in the performance of stochastic gradient descent (SGD), we propose and explore new Polyak-type variants suitable for the update rule of the SHB method. In pa"},"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":"2406.04142","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-06T15:08:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f1c6a2832cebc68157f16d267e26122ca785e0eafafd7e0b6a090e815452c177","abstract_canon_sha256":"41e34b34b26bfe87783f95ca2a5fdec91662252acc233de23c859a116c462701"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:19.863271Z","signature_b64":"Gm+aNqN2VtV/Y7aikCC+s4bezcJ0KbBdhL2By1MvisQ3j9YSbls+3wLjNwzFD7537ddtN6gzE7tIgW1rgvO8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142f8eded1bab4412ae213028e8cf9b8a1eec490689e0e25dcef86eab94f983d","last_reissued_at":"2026-07-05T10:23:19.862789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:19.862789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Dimitris Oikonomou, Nicolas Loizou","submitted_at":"2024-06-06T15:08:06Z","abstract_excerpt":"Stochastic gradient descent with momentum, also known as Stochastic Heavy Ball method (SHB), is one of the most popular algorithms for solving large-scale stochastic optimization problems in various machine learning tasks. In practical scenarios, tuning the step-size and momentum parameters of the method is a prohibitively expensive and time-consuming process. In this work, inspired by the recent advantages of stochastic Polyak step-size in the performance of stochastic gradient descent (SGD), we propose and explore new Polyak-type variants suitable for the update rule of the SHB method. In pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04142","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/2406.04142/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":"2406.04142","created_at":"2026-07-05T10:23:19.862847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04142v2","created_at":"2026-07-05T10:23:19.862847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04142","created_at":"2026-07-05T10:23:19.862847+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQXY5XWRXK2E","created_at":"2026-07-05T10:23:19.862847+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQXY5XWRXK2ECKXC","created_at":"2026-07-05T10:23:19.862847+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQXY5XWR","created_at":"2026-07-05T10:23:19.862847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.04988","citing_title":"Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07767","citing_title":"Taking the Road Less Scheduled with Adaptive Polyak Steps","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10183","citing_title":"Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC","json":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC.json","graph_json":"https://pith.science/api/pith-number/CQXY5XWRXK2ECKXCCMBI5DHZXC/graph.json","events_json":"https://pith.science/api/pith-number/CQXY5XWRXK2ECKXCCMBI5DHZXC/events.json","paper":"https://pith.science/paper/CQXY5XWR"},"agent_actions":{"view_html":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC","download_json":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC.json","view_paper":"https://pith.science/paper/CQXY5XWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04142&json=true","fetch_graph":"https://pith.science/api/pith-number/CQXY5XWRXK2ECKXCCMBI5DHZXC/graph.json","fetch_events":"https://pith.science/api/pith-number/CQXY5XWRXK2ECKXCCMBI5DHZXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC/action/storage_attestation","attest_author":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC/action/author_attestation","sign_citation":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC/action/citation_signature","submit_replication":"https://pith.science/pith/CQXY5XWRXK2ECKXCCMBI5DHZXC/action/replication_record"}},"created_at":"2026-07-05T10:23:19.862847+00:00","updated_at":"2026-07-05T10:23:19.862847+00:00"}