{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:35L3SYVACNFNXAGR3TA2R23YFT","short_pith_number":"pith:35L3SYVA","schema_version":"1.0","canonical_sha256":"df57b962a0134adb80d1dcc1a8eb782cd55f0b0d91416580e5ef6292bd96eb6d","source":{"kind":"arxiv","id":"1810.06801","version":4},"attestation_state":"computed","paper":{"title":"Quasi-hyperbolic momentum and Adam for deep learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Denis Yarats, Jerry Ma","submitted_at":"2018-10-16T03:58:14Z","abstract_excerpt":"Momentum-based acceleration of stochastic gradient descent (SGD) is widely used in deep learning. We propose the quasi-hyperbolic momentum algorithm (QHM) as an extremely simple alteration of momentum SGD, averaging a plain SGD step with a momentum step. We describe numerous connections to and identities with other algorithms, and we characterize the set of two-state optimization algorithms that QHM can recover. Finally, we propose a QH variant of Adam called QHAdam, and we empirically demonstrate that our algorithms lead to significantly improved training in a variety of settings, including a"},"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":"1810.06801","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T03:58:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bd8de8a473b30762c902bf352c36e9baffe83563754cfd8fbeb2d77836820446","abstract_canon_sha256":"352d70cb1556074e7773907e91ff167e650c4d2295dcd70cd9a6eaf381b98b3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:12.414612Z","signature_b64":"/kVvP1zVeu382rJYwb9pRbtseNnhevpPkeWNiSla30fKLdkrqNhJr797bOzAZPAL3HGeKFTCooyrd9eQxns/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df57b962a0134adb80d1dcc1a8eb782cd55f0b0d91416580e5ef6292bd96eb6d","last_reissued_at":"2026-05-17T23:47:12.414093Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:12.414093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quasi-hyperbolic momentum and Adam for deep learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Denis Yarats, Jerry Ma","submitted_at":"2018-10-16T03:58:14Z","abstract_excerpt":"Momentum-based acceleration of stochastic gradient descent (SGD) is widely used in deep learning. We propose the quasi-hyperbolic momentum algorithm (QHM) as an extremely simple alteration of momentum SGD, averaging a plain SGD step with a momentum step. We describe numerous connections to and identities with other algorithms, and we characterize the set of two-state optimization algorithms that QHM can recover. Finally, we propose a QH variant of Adam called QHAdam, and we empirically demonstrate that our algorithms lead to significantly improved training in a variety of settings, including a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06801","kind":"arxiv","version":4},"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":"1810.06801","created_at":"2026-05-17T23:47:12.414171+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.06801v4","created_at":"2026-05-17T23:47:12.414171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06801","created_at":"2026-05-17T23:47:12.414171+00:00"},{"alias_kind":"pith_short_12","alias_value":"35L3SYVACNFN","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"35L3SYVACNFNXAGR","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"35L3SYVA","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14108","citing_title":"Momentum Further Constrains Sharpness at the Edge of Stochastic Stability","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT","json":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT.json","graph_json":"https://pith.science/api/pith-number/35L3SYVACNFNXAGR3TA2R23YFT/graph.json","events_json":"https://pith.science/api/pith-number/35L3SYVACNFNXAGR3TA2R23YFT/events.json","paper":"https://pith.science/paper/35L3SYVA"},"agent_actions":{"view_html":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT","download_json":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT.json","view_paper":"https://pith.science/paper/35L3SYVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.06801&json=true","fetch_graph":"https://pith.science/api/pith-number/35L3SYVACNFNXAGR3TA2R23YFT/graph.json","fetch_events":"https://pith.science/api/pith-number/35L3SYVACNFNXAGR3TA2R23YFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT/action/storage_attestation","attest_author":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT/action/author_attestation","sign_citation":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT/action/citation_signature","submit_replication":"https://pith.science/pith/35L3SYVACNFNXAGR3TA2R23YFT/action/replication_record"}},"created_at":"2026-05-17T23:47:12.414171+00:00","updated_at":"2026-05-17T23:47:12.414171+00:00"}