{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:72Y25R3VTDPUH6SMIA3U2ERZVO","short_pith_number":"pith:72Y25R3V","schema_version":"1.0","canonical_sha256":"feb1aec77598df43fa4c40374d1239ab91de5da495694e0353d924902e90cc4a","source":{"kind":"arxiv","id":"1805.08095","version":1},"attestation_state":"computed","paper":{"title":"Small steps and giant leaps: Minimal Newton solvers for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Vedaldi, Jo\\~ao F. Henriques, Samuel Albanie, Sebastien Ehrhardt","submitted_at":"2018-05-21T14:54:28Z","abstract_excerpt":"We propose a fast second-order method that can be used as a drop-in replacement for current deep learning solvers. Compared to stochastic gradient descent (SGD), it only requires two additional forward-mode automatic differentiation operations per iteration, which has a computational cost comparable to two standard forward passes and is easy to implement. Our method addresses long-standing issues with current second-order solvers, which invert an approximate Hessian matrix every iteration exactly or by conjugate-gradient methods, a procedure that is both costly and sensitive to noise. Instead,"},"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":"1805.08095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T14:54:28Z","cross_cats_sorted":["cs.CV","cs.NA","stat.ML"],"title_canon_sha256":"b1b0d9dbf2498e19d5fe326c2ba0a0a0c73adfd2918ecdec75bca49ab88a4b01","abstract_canon_sha256":"47874dd60404517c42d98e72a4ad6b8114ad0181a07f6fd5cd07b5f4a5a9730d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:31.676794Z","signature_b64":"M7dg7toVgC+C5oO9X2IeV/W8NKZ2XjUEbQqAGBAGbDgsjuEzv+jwAYhBKpix91unSgLY640ym1Gg4M4EXbj1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feb1aec77598df43fa4c40374d1239ab91de5da495694e0353d924902e90cc4a","last_reissued_at":"2026-05-18T00:15:31.676036Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:31.676036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small steps and giant leaps: Minimal Newton solvers for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Vedaldi, Jo\\~ao F. Henriques, Samuel Albanie, Sebastien Ehrhardt","submitted_at":"2018-05-21T14:54:28Z","abstract_excerpt":"We propose a fast second-order method that can be used as a drop-in replacement for current deep learning solvers. Compared to stochastic gradient descent (SGD), it only requires two additional forward-mode automatic differentiation operations per iteration, which has a computational cost comparable to two standard forward passes and is easy to implement. Our method addresses long-standing issues with current second-order solvers, which invert an approximate Hessian matrix every iteration exactly or by conjugate-gradient methods, a procedure that is both costly and sensitive to noise. Instead,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08095","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":""},"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":"1805.08095","created_at":"2026-05-18T00:15:31.676151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08095v1","created_at":"2026-05-18T00:15:31.676151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08095","created_at":"2026-05-18T00:15:31.676151+00:00"},{"alias_kind":"pith_short_12","alias_value":"72Y25R3VTDPU","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"72Y25R3VTDPUH6SM","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"72Y25R3V","created_at":"2026-05-18T12:32:11.075285+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/72Y25R3VTDPUH6SMIA3U2ERZVO","json":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO.json","graph_json":"https://pith.science/api/pith-number/72Y25R3VTDPUH6SMIA3U2ERZVO/graph.json","events_json":"https://pith.science/api/pith-number/72Y25R3VTDPUH6SMIA3U2ERZVO/events.json","paper":"https://pith.science/paper/72Y25R3V"},"agent_actions":{"view_html":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO","download_json":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO.json","view_paper":"https://pith.science/paper/72Y25R3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08095&json=true","fetch_graph":"https://pith.science/api/pith-number/72Y25R3VTDPUH6SMIA3U2ERZVO/graph.json","fetch_events":"https://pith.science/api/pith-number/72Y25R3VTDPUH6SMIA3U2ERZVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO/action/storage_attestation","attest_author":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO/action/author_attestation","sign_citation":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO/action/citation_signature","submit_replication":"https://pith.science/pith/72Y25R3VTDPUH6SMIA3U2ERZVO/action/replication_record"}},"created_at":"2026-05-18T00:15:31.676151+00:00","updated_at":"2026-05-18T00:15:31.676151+00:00"}