{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T66DJAL2NMLYFXOEZAUSG645FN","short_pith_number":"pith:T66DJAL2","schema_version":"1.0","canonical_sha256":"9fbc34817a6b1782ddc4c829237b9d2b4b9c2afca68121f7a1c80fee7a86d04f","source":{"kind":"arxiv","id":"2407.02772","version":3},"attestation_state":"computed","paper":{"title":"Gradient descent with generalized Newton's method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Shiyun Xu, Zhiqi Bu","submitted_at":"2024-07-03T03:01:43Z","abstract_excerpt":"We propose the generalized Newton's method (GeN) -- a Hessian-informed approach that applies to any optimizer such as SGD and Adam, and covers the Newton-Raphson method as a sub-case. Our method automatically and dynamically selects the learning rate that accelerates the convergence, without the intensive tuning of the learning rate scheduler. In practice, our method is easily implementable, since it only requires additional forward passes with almost zero computational overhead (in terms of training time and memory cost), if the overhead is amortized over many iterations. We present extensive"},"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":"2407.02772","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T03:01:43Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"1c187669783db70d959ee6f81094e13f51af5ae37229395635aa7fc3a577fe39","abstract_canon_sha256":"edb20938ce2aa387b6b55b057f4aee61b8789bdfa4a93fa0b1d37de17ef392ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:38.227795Z","signature_b64":"fxWSVkspZA/JhLOgDJ3XYOKP1xORWS23s190o6e5QRgXSti2dr4tGAFwXbOy/8pWcOtRJ2v6Rd/DPb7Zux6QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fbc34817a6b1782ddc4c829237b9d2b4b9c2afca68121f7a1c80fee7a86d04f","last_reissued_at":"2026-07-05T11:04:38.227273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:38.227273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient descent with generalized Newton's method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Shiyun Xu, Zhiqi Bu","submitted_at":"2024-07-03T03:01:43Z","abstract_excerpt":"We propose the generalized Newton's method (GeN) -- a Hessian-informed approach that applies to any optimizer such as SGD and Adam, and covers the Newton-Raphson method as a sub-case. Our method automatically and dynamically selects the learning rate that accelerates the convergence, without the intensive tuning of the learning rate scheduler. In practice, our method is easily implementable, since it only requires additional forward passes with almost zero computational overhead (in terms of training time and memory cost), if the overhead is amortized over many iterations. We present extensive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02772","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/2407.02772/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":"2407.02772","created_at":"2026-07-05T11:04:38.227346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02772v3","created_at":"2026-07-05T11:04:38.227346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02772","created_at":"2026-07-05T11:04:38.227346+00:00"},{"alias_kind":"pith_short_12","alias_value":"T66DJAL2NMLY","created_at":"2026-07-05T11:04:38.227346+00:00"},{"alias_kind":"pith_short_16","alias_value":"T66DJAL2NMLYFXOE","created_at":"2026-07-05T11:04:38.227346+00:00"},{"alias_kind":"pith_short_8","alias_value":"T66DJAL2","created_at":"2026-07-05T11:04:38.227346+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/T66DJAL2NMLYFXOEZAUSG645FN","json":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN.json","graph_json":"https://pith.science/api/pith-number/T66DJAL2NMLYFXOEZAUSG645FN/graph.json","events_json":"https://pith.science/api/pith-number/T66DJAL2NMLYFXOEZAUSG645FN/events.json","paper":"https://pith.science/paper/T66DJAL2"},"agent_actions":{"view_html":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN","download_json":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN.json","view_paper":"https://pith.science/paper/T66DJAL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02772&json=true","fetch_graph":"https://pith.science/api/pith-number/T66DJAL2NMLYFXOEZAUSG645FN/graph.json","fetch_events":"https://pith.science/api/pith-number/T66DJAL2NMLYFXOEZAUSG645FN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN/action/storage_attestation","attest_author":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN/action/author_attestation","sign_citation":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN/action/citation_signature","submit_replication":"https://pith.science/pith/T66DJAL2NMLYFXOEZAUSG645FN/action/replication_record"}},"created_at":"2026-07-05T11:04:38.227346+00:00","updated_at":"2026-07-05T11:04:38.227346+00:00"}