{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QORIT5CK4WDBFWNYAAB5RBBPWC","short_pith_number":"pith:QORIT5CK","schema_version":"1.0","canonical_sha256":"83a289f44ae58612d9b80003d8842fb0bff04dc95a149ebceb857e812bee1783","source":{"kind":"arxiv","id":"2111.11828","version":1},"attestation_state":"computed","paper":{"title":"Variance Reduction in Deep Learning: More Momentum is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Lionel Tondji, Moustapha Cisse, Sergii Kashubin","submitted_at":"2021-11-23T12:48:52Z","abstract_excerpt":"Variance reduction (VR) techniques have contributed significantly to accelerating learning with massive datasets in the smooth and strongly convex setting (Schmidt et al., 2017; Johnson & Zhang, 2013; Roux et al., 2012). However, such techniques have not yet met the same success in the realm of large-scale deep learning due to various factors such as the use of data augmentation or regularization methods like dropout (Defazio & Bottou, 2019). This challenge has recently motivated the design of novel variance reduction techniques tailored explicitly for deep learning (Arnold et al., 2019; Ma & "},"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":"2111.11828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-23T12:48:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"733a0cca3c22697e6129aa10229fda15fcfe9ba26dfb4132f6026b20dec6332a","abstract_canon_sha256":"585f7e2f931a1a988b2c655fb19935f4c3727a597b775c4526da3512692b54dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:13.204285Z","signature_b64":"GpNnRlUNxLgsfS7n7YGE3Vw+ehB3/9sU/Jh4sMjJr8s4uDYbVHzGJNPcODm5vraEdIQPuyPXzWY4/LGnSxiLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83a289f44ae58612d9b80003d8842fb0bff04dc95a149ebceb857e812bee1783","last_reissued_at":"2026-07-05T03:34:13.203898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:13.203898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance Reduction in Deep Learning: More Momentum is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Lionel Tondji, Moustapha Cisse, Sergii Kashubin","submitted_at":"2021-11-23T12:48:52Z","abstract_excerpt":"Variance reduction (VR) techniques have contributed significantly to accelerating learning with massive datasets in the smooth and strongly convex setting (Schmidt et al., 2017; Johnson & Zhang, 2013; Roux et al., 2012). However, such techniques have not yet met the same success in the realm of large-scale deep learning due to various factors such as the use of data augmentation or regularization methods like dropout (Defazio & Bottou, 2019). This challenge has recently motivated the design of novel variance reduction techniques tailored explicitly for deep learning (Arnold et al., 2019; Ma & "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11828","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/2111.11828/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":"2111.11828","created_at":"2026-07-05T03:34:13.203954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11828v1","created_at":"2026-07-05T03:34:13.203954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11828","created_at":"2026-07-05T03:34:13.203954+00:00"},{"alias_kind":"pith_short_12","alias_value":"QORIT5CK4WDB","created_at":"2026-07-05T03:34:13.203954+00:00"},{"alias_kind":"pith_short_16","alias_value":"QORIT5CK4WDBFWNY","created_at":"2026-07-05T03:34:13.203954+00:00"},{"alias_kind":"pith_short_8","alias_value":"QORIT5CK","created_at":"2026-07-05T03:34:13.203954+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/QORIT5CK4WDBFWNYAAB5RBBPWC","json":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC.json","graph_json":"https://pith.science/api/pith-number/QORIT5CK4WDBFWNYAAB5RBBPWC/graph.json","events_json":"https://pith.science/api/pith-number/QORIT5CK4WDBFWNYAAB5RBBPWC/events.json","paper":"https://pith.science/paper/QORIT5CK"},"agent_actions":{"view_html":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC","download_json":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC.json","view_paper":"https://pith.science/paper/QORIT5CK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11828&json=true","fetch_graph":"https://pith.science/api/pith-number/QORIT5CK4WDBFWNYAAB5RBBPWC/graph.json","fetch_events":"https://pith.science/api/pith-number/QORIT5CK4WDBFWNYAAB5RBBPWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC/action/storage_attestation","attest_author":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC/action/author_attestation","sign_citation":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC/action/citation_signature","submit_replication":"https://pith.science/pith/QORIT5CK4WDBFWNYAAB5RBBPWC/action/replication_record"}},"created_at":"2026-07-05T03:34:13.203954+00:00","updated_at":"2026-07-05T03:34:13.203954+00:00"}