{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PYUN7AH5NV3NPDLPWK35XWH2AQ","short_pith_number":"pith:PYUN7AH5","schema_version":"1.0","canonical_sha256":"7e28df80fd6d76d78d6fb2b7dbd8fa0409c206d877ebdb75c92cf4971c77b0f0","source":{"kind":"arxiv","id":"2102.07314","version":1},"attestation_state":"computed","paper":{"title":"The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gaowei Wu, Qing Tao, Sheng Long, Wei Tao","submitted_at":"2021-02-15T02:57:14Z","abstract_excerpt":"The adaptive stochastic gradient descent (SGD) with momentum has been widely adopted in deep learning as well as convex optimization. In practice, the last iterate is commonly used as the final solution to make decisions. However, the available regret analysis and the setting of constant momentum parameters only guarantee the optimal convergence of the averaged solution. In this paper, we fill this theory-practice gap by investigating the convergence of the last iterate (referred to as individual convergence), which is a more difficult task than convergence analysis of the averaged solution. S"},"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":"2102.07314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-15T02:57:14Z","cross_cats_sorted":[],"title_canon_sha256":"9a13e629ff2cd55601657ef1a5002d4a5bab199240063a56b59ebf20d93e92ea","abstract_canon_sha256":"2f5ccccfd30a82d39bd70475d0cac76fd5dd792c33563e0b79a22f3338b4746c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:14.699930Z","signature_b64":"CZ9yxnCEk/d5GcR0N80FFPenPnVgbtRMOp6ouudGaG9i7qRhlpI06bOXg10H59Ll1+Tp9sL+YeUShnnatEh+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e28df80fd6d76d78d6fb2b7dbd8fa0409c206d877ebdb75c92cf4971c77b0f0","last_reissued_at":"2026-07-05T02:15:14.699570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:14.699570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gaowei Wu, Qing Tao, Sheng Long, Wei Tao","submitted_at":"2021-02-15T02:57:14Z","abstract_excerpt":"The adaptive stochastic gradient descent (SGD) with momentum has been widely adopted in deep learning as well as convex optimization. In practice, the last iterate is commonly used as the final solution to make decisions. However, the available regret analysis and the setting of constant momentum parameters only guarantee the optimal convergence of the averaged solution. In this paper, we fill this theory-practice gap by investigating the convergence of the last iterate (referred to as individual convergence), which is a more difficult task than convergence analysis of the averaged solution. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07314","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/2102.07314/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":"2102.07314","created_at":"2026-07-05T02:15:14.699629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07314v1","created_at":"2026-07-05T02:15:14.699629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07314","created_at":"2026-07-05T02:15:14.699629+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYUN7AH5NV3N","created_at":"2026-07-05T02:15:14.699629+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYUN7AH5NV3NPDLP","created_at":"2026-07-05T02:15:14.699629+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYUN7AH5","created_at":"2026-07-05T02:15:14.699629+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/PYUN7AH5NV3NPDLPWK35XWH2AQ","json":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ.json","graph_json":"https://pith.science/api/pith-number/PYUN7AH5NV3NPDLPWK35XWH2AQ/graph.json","events_json":"https://pith.science/api/pith-number/PYUN7AH5NV3NPDLPWK35XWH2AQ/events.json","paper":"https://pith.science/paper/PYUN7AH5"},"agent_actions":{"view_html":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ","download_json":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ.json","view_paper":"https://pith.science/paper/PYUN7AH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07314&json=true","fetch_graph":"https://pith.science/api/pith-number/PYUN7AH5NV3NPDLPWK35XWH2AQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PYUN7AH5NV3NPDLPWK35XWH2AQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ/action/storage_attestation","attest_author":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ/action/author_attestation","sign_citation":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ/action/citation_signature","submit_replication":"https://pith.science/pith/PYUN7AH5NV3NPDLPWK35XWH2AQ/action/replication_record"}},"created_at":"2026-07-05T02:15:14.699629+00:00","updated_at":"2026-07-05T02:15:14.699629+00:00"}