{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FNP252XIIMURMCI6X7ZFT35JQW","short_pith_number":"pith:FNP252XI","schema_version":"1.0","canonical_sha256":"2b5faeeae8432916091ebff259efa985a6bc9fa38709353d0b2698e70cd998b8","source":{"kind":"arxiv","id":"1601.04737","version":3},"attestation_state":"computed","paper":{"title":"Sub-Sampled Newton Methods I: Globally Convergent Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Farbod Roosta-Khorasani, Michael W. Mahoney","submitted_at":"2016-01-18T21:59:21Z","abstract_excerpt":"Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the computations and/or to implicitly implement a form of statistical regularization. In this paper, we consider second-order iterative optimization algorithms and we provide bounds on the convergence of the variants of Newton's method that incorporate uniform sub-sampling as a means to estimate the gradient and/or Hessian. Our bounds are non-asymptotic and quantitative. "},"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":"1601.04737","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-01-18T21:59:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c5f787fbf2a2d154327eabff6bce3d47a7264f8c57b85c14fb9cab3f828d85cd","abstract_canon_sha256":"2f0238bcfeecfd2d329677960f57b8dd17013b7e7ec8395167a59e8efdb3f352"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:56.982340Z","signature_b64":"gt1zRhOS5Rp4IvVsMbJDTqr5ypNFVdljyfAoZLgHBdDJ7atLbeFjXf+dDdBS8bCCUQTF23hu93AP8FYAFLMADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b5faeeae8432916091ebff259efa985a6bc9fa38709353d0b2698e70cd998b8","last_reissued_at":"2026-05-18T01:19:56.981559Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:56.981559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sub-Sampled Newton Methods I: Globally Convergent Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Farbod Roosta-Khorasani, Michael W. Mahoney","submitted_at":"2016-01-18T21:59:21Z","abstract_excerpt":"Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the computations and/or to implicitly implement a form of statistical regularization. In this paper, we consider second-order iterative optimization algorithms and we provide bounds on the convergence of the variants of Newton's method that incorporate uniform sub-sampling as a means to estimate the gradient and/or Hessian. Our bounds are non-asymptotic and quantitative. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.04737","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":""},"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":"1601.04737","created_at":"2026-05-18T01:19:56.981699+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.04737v3","created_at":"2026-05-18T01:19:56.981699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.04737","created_at":"2026-05-18T01:19:56.981699+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNP252XIIMUR","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNP252XIIMURMCI6","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNP252XI","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06350","citing_title":"SMOP: Stochastic trust region method for multi-objective problems","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW","json":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW.json","graph_json":"https://pith.science/api/pith-number/FNP252XIIMURMCI6X7ZFT35JQW/graph.json","events_json":"https://pith.science/api/pith-number/FNP252XIIMURMCI6X7ZFT35JQW/events.json","paper":"https://pith.science/paper/FNP252XI"},"agent_actions":{"view_html":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW","download_json":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW.json","view_paper":"https://pith.science/paper/FNP252XI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.04737&json=true","fetch_graph":"https://pith.science/api/pith-number/FNP252XIIMURMCI6X7ZFT35JQW/graph.json","fetch_events":"https://pith.science/api/pith-number/FNP252XIIMURMCI6X7ZFT35JQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW/action/storage_attestation","attest_author":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW/action/author_attestation","sign_citation":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW/action/citation_signature","submit_replication":"https://pith.science/pith/FNP252XIIMURMCI6X7ZFT35JQW/action/replication_record"}},"created_at":"2026-05-18T01:19:56.981699+00:00","updated_at":"2026-05-18T01:19:56.981699+00:00"}