{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:43A4N4M3ACCJ5K4KSL2J3VRGQE","short_pith_number":"pith:43A4N4M3","schema_version":"1.0","canonical_sha256":"e6c1c6f19b00849eab8a92f49dd6268133932e0ab138a24b70fe68671e8bc186","source":{"kind":"arxiv","id":"1712.09677","version":2},"attestation_state":"computed","paper":{"title":"Momentum and Stochastic Momentum for Stochastic Gradient, Newton, Proximal Point and Subspace Descent Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Nicolas Loizou, Peter Richt\\'arik","submitted_at":"2017-12-27T20:40:24Z","abstract_excerpt":"In this paper we study several classes of stochastic optimization algorithms enriched with heavy ball momentum. Among the methods studied are: stochastic gradient descent, stochastic Newton, stochastic proximal point and stochastic dual subspace ascent. This is the first time momentum variants of several of these methods are studied. We choose to perform our analysis in a setting in which all of the above methods are equivalent. We prove global nonassymptotic linear convergence rates for all methods and various measures of success, including primal function values, primal iterates (in L2 sense"},"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":"1712.09677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-12-27T20:40:24Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","stat.ML"],"title_canon_sha256":"72796094aacd430f343a62171248187596fb8066995cb56949ce70f8c2a258ac","abstract_canon_sha256":"e4c099913ed87aa0a718e48f15db4b1a80d81d8454ad0b1589564bcb70b8f298"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:53.201758Z","signature_b64":"sF6OP2Kqx3zi6yrnCXnuOVawU4l2ymm5eKvctWBfJOBVfvTqMPIp3J88zOJL+qjpGbjGUILschCffuq1kQGICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6c1c6f19b00849eab8a92f49dd6268133932e0ab138a24b70fe68671e8bc186","last_reissued_at":"2026-05-18T00:19:53.201038Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:53.201038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Momentum and Stochastic Momentum for Stochastic Gradient, Newton, Proximal Point and Subspace Descent Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Nicolas Loizou, Peter Richt\\'arik","submitted_at":"2017-12-27T20:40:24Z","abstract_excerpt":"In this paper we study several classes of stochastic optimization algorithms enriched with heavy ball momentum. Among the methods studied are: stochastic gradient descent, stochastic Newton, stochastic proximal point and stochastic dual subspace ascent. This is the first time momentum variants of several of these methods are studied. We choose to perform our analysis in a setting in which all of the above methods are equivalent. We prove global nonassymptotic linear convergence rates for all methods and various measures of success, including primal function values, primal iterates (in L2 sense"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09677","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":""},"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":"1712.09677","created_at":"2026-05-18T00:19:53.201151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09677v2","created_at":"2026-05-18T00:19:53.201151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09677","created_at":"2026-05-18T00:19:53.201151+00:00"},{"alias_kind":"pith_short_12","alias_value":"43A4N4M3ACCJ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"43A4N4M3ACCJ5K4K","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"43A4N4M3","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09697","citing_title":"Heavy-ball Algorithms Always Escape Saddle Points","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE","json":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE.json","graph_json":"https://pith.science/api/pith-number/43A4N4M3ACCJ5K4KSL2J3VRGQE/graph.json","events_json":"https://pith.science/api/pith-number/43A4N4M3ACCJ5K4KSL2J3VRGQE/events.json","paper":"https://pith.science/paper/43A4N4M3"},"agent_actions":{"view_html":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE","download_json":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE.json","view_paper":"https://pith.science/paper/43A4N4M3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09677&json=true","fetch_graph":"https://pith.science/api/pith-number/43A4N4M3ACCJ5K4KSL2J3VRGQE/graph.json","fetch_events":"https://pith.science/api/pith-number/43A4N4M3ACCJ5K4KSL2J3VRGQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE/action/storage_attestation","attest_author":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE/action/author_attestation","sign_citation":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE/action/citation_signature","submit_replication":"https://pith.science/pith/43A4N4M3ACCJ5K4KSL2J3VRGQE/action/replication_record"}},"created_at":"2026-05-18T00:19:53.201151+00:00","updated_at":"2026-05-18T00:19:53.201151+00:00"}