{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2JZ5MTG3EP6RQBZTXK7SVFOT3F","short_pith_number":"pith:2JZ5MTG3","schema_version":"1.0","canonical_sha256":"d273d64cdb23fd180733babf2a95d3d9747bddaaa16b9d6f6849915597855e52","source":{"kind":"arxiv","id":"2506.11904","version":2},"attestation_state":"computed","paper":{"title":"Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Mathukumalli Vidyasagar","submitted_at":"2025-06-13T15:53:17Z","abstract_excerpt":"In this paper, we present a unified algorithm for stochastic optimization that makes use of a \"momentum\" term; in other words, the stochastic gradient depends not only on the current true gradient of the objective function, but also on the true gradient at the previous iteration. Our formulation includes the Stochastic Heavy Ball (SHB) and the Stochastic Nesterov Accelerated Gradient (SNAG) algorithms as special cases. In addition, in our formulation, the momentum term is allowed to vary as a function of time (i.e., the iteration counter). The assumptions on the stochastic gradient are the mos"},"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":"2506.11904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-13T15:53:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d7ac8453f108be1755892a7335fa506015ea50e2d660a39ac6a34b29db1a3f6c","abstract_canon_sha256":"2ba3f045c8f8cb7b2e733aea17f6f490a1d4f148f08e24a4de9f516cb43f6acc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:38.877271Z","signature_b64":"43lnp2x0uKY9cofDDn4HMXDKTtPm/rLlyDBUOnPdeJ0lx91lp1eOdRZqq8uffidHg5LFgQAzJ46LTSQWVxobBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d273d64cdb23fd180733babf2a95d3d9747bddaaa16b9d6f6849915597855e52","last_reissued_at":"2026-07-05T12:07:38.876749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:38.876749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Mathukumalli Vidyasagar","submitted_at":"2025-06-13T15:53:17Z","abstract_excerpt":"In this paper, we present a unified algorithm for stochastic optimization that makes use of a \"momentum\" term; in other words, the stochastic gradient depends not only on the current true gradient of the objective function, but also on the true gradient at the previous iteration. Our formulation includes the Stochastic Heavy Ball (SHB) and the Stochastic Nesterov Accelerated Gradient (SNAG) algorithms as special cases. In addition, in our formulation, the momentum term is allowed to vary as a function of time (i.e., the iteration counter). The assumptions on the stochastic gradient are the mos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11904","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/2506.11904/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":"2506.11904","created_at":"2026-07-05T12:07:38.876815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11904v2","created_at":"2026-07-05T12:07:38.876815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11904","created_at":"2026-07-05T12:07:38.876815+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JZ5MTG3EP6R","created_at":"2026-07-05T12:07:38.876815+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JZ5MTG3EP6RQBZT","created_at":"2026-07-05T12:07:38.876815+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JZ5MTG3","created_at":"2026-07-05T12:07:38.876815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.12238","citing_title":"On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F","json":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F.json","graph_json":"https://pith.science/api/pith-number/2JZ5MTG3EP6RQBZTXK7SVFOT3F/graph.json","events_json":"https://pith.science/api/pith-number/2JZ5MTG3EP6RQBZTXK7SVFOT3F/events.json","paper":"https://pith.science/paper/2JZ5MTG3"},"agent_actions":{"view_html":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F","download_json":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F.json","view_paper":"https://pith.science/paper/2JZ5MTG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11904&json=true","fetch_graph":"https://pith.science/api/pith-number/2JZ5MTG3EP6RQBZTXK7SVFOT3F/graph.json","fetch_events":"https://pith.science/api/pith-number/2JZ5MTG3EP6RQBZTXK7SVFOT3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F/action/storage_attestation","attest_author":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F/action/author_attestation","sign_citation":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F/action/citation_signature","submit_replication":"https://pith.science/pith/2JZ5MTG3EP6RQBZTXK7SVFOT3F/action/replication_record"}},"created_at":"2026-07-05T12:07:38.876815+00:00","updated_at":"2026-07-05T12:07:38.876815+00:00"}