{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AAEVN35KKYJG6DASTGBTFAPSYJ","short_pith_number":"pith:AAEVN35K","schema_version":"1.0","canonical_sha256":"000956efaa56126f0c1299833281f2c24844559368fbf3b7548a671de3a79dc5","source":{"kind":"arxiv","id":"1909.01238","version":1},"attestation_state":"computed","paper":{"title":"Stochastic quasi-Newton with line-search regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"eess.SY","authors_text":"Adrian Wills, Thomas Sch\\\"on","submitted_at":"2019-09-03T15:10:42Z","abstract_excerpt":"In this paper we present a novel quasi-Newton algorithm for use in stochastic optimisation. Quasi-Newton methods have had an enormous impact on deterministic optimisation problems because they afford rapid convergence and computationally attractive algorithms. In essence, this is achieved by learning the second-order (Hessian) information based on observing first-order gradients. We extend these ideas to the stochastic setting by employing a highly flexible model for the Hessian and infer its value based on observing noisy gradients. In addition, we propose a stochastic counterpart to standard"},"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":"1909.01238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-09-03T15:10:42Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"20cb35d5c9c55ab527428ee0bd3bfea55257f7436d6d3baa8ef5ff26f57f8564","abstract_canon_sha256":"0c60cdfa49c72b8d76c0a8db9f5c03666277dafa7daaf379c0b33f1f12d152b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:17.220058Z","signature_b64":"KrM8Ll0sSo/CqRLNIYl9ZQaUXHWbRPHILXviBNfTGs5qIvP5xEAHJnlw0Gdx+bWC/r2l0Wntd10pxEA8p4m/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"000956efaa56126f0c1299833281f2c24844559368fbf3b7548a671de3a79dc5","last_reissued_at":"2026-07-05T00:01:17.219605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:17.219605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic quasi-Newton with line-search regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"eess.SY","authors_text":"Adrian Wills, Thomas Sch\\\"on","submitted_at":"2019-09-03T15:10:42Z","abstract_excerpt":"In this paper we present a novel quasi-Newton algorithm for use in stochastic optimisation. Quasi-Newton methods have had an enormous impact on deterministic optimisation problems because they afford rapid convergence and computationally attractive algorithms. In essence, this is achieved by learning the second-order (Hessian) information based on observing first-order gradients. We extend these ideas to the stochastic setting by employing a highly flexible model for the Hessian and infer its value based on observing noisy gradients. In addition, we propose a stochastic counterpart to standard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01238","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/1909.01238/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":"1909.01238","created_at":"2026-07-05T00:01:17.219666+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01238v1","created_at":"2026-07-05T00:01:17.219666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01238","created_at":"2026-07-05T00:01:17.219666+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAEVN35KKYJG","created_at":"2026-07-05T00:01:17.219666+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAEVN35KKYJG6DAS","created_at":"2026-07-05T00:01:17.219666+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAEVN35K","created_at":"2026-07-05T00:01:17.219666+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/AAEVN35KKYJG6DASTGBTFAPSYJ","json":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ.json","graph_json":"https://pith.science/api/pith-number/AAEVN35KKYJG6DASTGBTFAPSYJ/graph.json","events_json":"https://pith.science/api/pith-number/AAEVN35KKYJG6DASTGBTFAPSYJ/events.json","paper":"https://pith.science/paper/AAEVN35K"},"agent_actions":{"view_html":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ","download_json":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ.json","view_paper":"https://pith.science/paper/AAEVN35K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01238&json=true","fetch_graph":"https://pith.science/api/pith-number/AAEVN35KKYJG6DASTGBTFAPSYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AAEVN35KKYJG6DASTGBTFAPSYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ/action/storage_attestation","attest_author":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ/action/author_attestation","sign_citation":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ/action/citation_signature","submit_replication":"https://pith.science/pith/AAEVN35KKYJG6DASTGBTFAPSYJ/action/replication_record"}},"created_at":"2026-07-05T00:01:17.219666+00:00","updated_at":"2026-07-05T00:01:17.219666+00:00"}