{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5FJWLCVTGF3YBVGKIOECUMJ7BR","short_pith_number":"pith:5FJWLCVT","schema_version":"1.0","canonical_sha256":"e953658ab3317780d4ca43882a313f0c5d04beba6e049f1367644bdae98bd4e1","source":{"kind":"arxiv","id":"1905.10018","version":3},"attestation_state":"computed","paper":{"title":"Momentum-Based Variance Reduction in Non-Convex SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashok Cutkosky, Francesco Orabona","submitted_at":"2019-05-24T03:21:07Z","abstract_excerpt":"Variance reduction has emerged in recent years as a strong competitor to stochastic gradient descent in non-convex problems, providing the first algorithms to improve upon the converge rate of stochastic gradient descent for finding first-order critical points. However, variance reduction techniques typically require carefully tuned learning rates and willingness to use excessively large \"mega-batches\" in order to achieve their improved results. We present a new algorithm, STORM, that does not require any batches and makes use of adaptive learning rates, enabling simpler implementation and les"},"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":"1905.10018","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T03:21:07Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f03c88ca0cfa9346468d97bf4cbd95b707b8dd608e853d04bf5d1fd41fcb0623","abstract_canon_sha256":"7e52c3d5ad18d78635056ac57be1b7ad018f2148ac5fd75bbab7f29ef0f552fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:22.871385Z","signature_b64":"aWOpxzAolM14Zl6Xz3vILz4ZuqR/6if+cE6uHliGYtpYHN4z7qF7bJYJkd0Kg630hkSLe7fv732zTAwJH/SXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e953658ab3317780d4ca43882a313f0c5d04beba6e049f1367644bdae98bd4e1","last_reissued_at":"2026-07-05T00:57:22.870905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:22.870905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Momentum-Based Variance Reduction in Non-Convex SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashok Cutkosky, Francesco Orabona","submitted_at":"2019-05-24T03:21:07Z","abstract_excerpt":"Variance reduction has emerged in recent years as a strong competitor to stochastic gradient descent in non-convex problems, providing the first algorithms to improve upon the converge rate of stochastic gradient descent for finding first-order critical points. However, variance reduction techniques typically require carefully tuned learning rates and willingness to use excessively large \"mega-batches\" in order to achieve their improved results. We present a new algorithm, STORM, that does not require any batches and makes use of adaptive learning rates, enabling simpler implementation and les"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10018","kind":"arxiv","version":3},"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/1905.10018/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":"1905.10018","created_at":"2026-07-05T00:57:22.870966+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10018v3","created_at":"2026-07-05T00:57:22.870966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10018","created_at":"2026-07-05T00:57:22.870966+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FJWLCVTGF3Y","created_at":"2026-07-05T00:57:22.870966+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FJWLCVTGF3YBVGK","created_at":"2026-07-05T00:57:22.870966+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FJWLCVT","created_at":"2026-07-05T00:57:22.870966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.15816","citing_title":"On the Convergence of Muon and Beyond","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28254","citing_title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR","json":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR.json","graph_json":"https://pith.science/api/pith-number/5FJWLCVTGF3YBVGKIOECUMJ7BR/graph.json","events_json":"https://pith.science/api/pith-number/5FJWLCVTGF3YBVGKIOECUMJ7BR/events.json","paper":"https://pith.science/paper/5FJWLCVT"},"agent_actions":{"view_html":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR","download_json":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR.json","view_paper":"https://pith.science/paper/5FJWLCVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10018&json=true","fetch_graph":"https://pith.science/api/pith-number/5FJWLCVTGF3YBVGKIOECUMJ7BR/graph.json","fetch_events":"https://pith.science/api/pith-number/5FJWLCVTGF3YBVGKIOECUMJ7BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR/action/storage_attestation","attest_author":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR/action/author_attestation","sign_citation":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR/action/citation_signature","submit_replication":"https://pith.science/pith/5FJWLCVTGF3YBVGKIOECUMJ7BR/action/replication_record"}},"created_at":"2026-07-05T00:57:22.870966+00:00","updated_at":"2026-07-05T00:57:22.870966+00:00"}