{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6W4POCKDMJYAGQZW3IKZKECZJ6","short_pith_number":"pith:6W4POCKD","schema_version":"1.0","canonical_sha256":"f5b8f709436270034336da159510594fa90ddf74b47d012fb5233eff5d9037dd","source":{"kind":"arxiv","id":"1802.04310","version":1},"attestation_state":"computed","paper":{"title":"Stochastic quasi-Newton with adaptive step lengths for large-scale problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adrian Wills, Thomas Sch\\\"on","submitted_at":"2018-02-12T19:13:28Z","abstract_excerpt":"We provide a numerically robust and fast method capable of exploiting the local geometry when solving large-scale stochastic optimisation problems. Our key innovation is an auxiliary variable construction coupled with an inverse Hessian approximation computed using a receding history of iterates and gradients. It is the Markov chain nature of the classic stochastic gradient algorithm that enables this development. The construction offers a mechanism for stochastic line search adapting the step length. We numerically evaluate and compare against current state-of-the-art with encouraging perform"},"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":"1802.04310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-12T19:13:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"57964cac3a8bc7078ebc674521f52027be722c0b84b812577ee1ff0fd35c4ed0","abstract_canon_sha256":"24f3d67b590dddff2a863b3035cd05e3b81bf51d649b8e4e4dc383751fb122e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:44.569775Z","signature_b64":"NfhcB+yU5YawRN/rKT+/0VkmXfmKWb/ZVD2OQOVvE8qk1P17/mS0Ub7TPGO5JMqEEJp6vRRTZQjLQolszf/5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b8f709436270034336da159510594fa90ddf74b47d012fb5233eff5d9037dd","last_reissued_at":"2026-05-18T00:23:44.569307Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:44.569307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic quasi-Newton with adaptive step lengths for large-scale problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adrian Wills, Thomas Sch\\\"on","submitted_at":"2018-02-12T19:13:28Z","abstract_excerpt":"We provide a numerically robust and fast method capable of exploiting the local geometry when solving large-scale stochastic optimisation problems. Our key innovation is an auxiliary variable construction coupled with an inverse Hessian approximation computed using a receding history of iterates and gradients. It is the Markov chain nature of the classic stochastic gradient algorithm that enables this development. The construction offers a mechanism for stochastic line search adapting the step length. We numerically evaluate and compare against current state-of-the-art with encouraging perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04310","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":"1802.04310","created_at":"2026-05-18T00:23:44.569387+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04310v1","created_at":"2026-05-18T00:23:44.569387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04310","created_at":"2026-05-18T00:23:44.569387+00:00"},{"alias_kind":"pith_short_12","alias_value":"6W4POCKDMJYA","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6W4POCKDMJYAGQZW","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6W4POCKD","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2212.08989","citing_title":"Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics","ref_index":148,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6","json":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6.json","graph_json":"https://pith.science/api/pith-number/6W4POCKDMJYAGQZW3IKZKECZJ6/graph.json","events_json":"https://pith.science/api/pith-number/6W4POCKDMJYAGQZW3IKZKECZJ6/events.json","paper":"https://pith.science/paper/6W4POCKD"},"agent_actions":{"view_html":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6","download_json":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6.json","view_paper":"https://pith.science/paper/6W4POCKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04310&json=true","fetch_graph":"https://pith.science/api/pith-number/6W4POCKDMJYAGQZW3IKZKECZJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/6W4POCKDMJYAGQZW3IKZKECZJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6/action/storage_attestation","attest_author":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6/action/author_attestation","sign_citation":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6/action/citation_signature","submit_replication":"https://pith.science/pith/6W4POCKDMJYAGQZW3IKZKECZJ6/action/replication_record"}},"created_at":"2026-05-18T00:23:44.569387+00:00","updated_at":"2026-05-18T00:23:44.569387+00:00"}