{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:EXYO3IG4BCOFJ6OBUQTBUU764U","short_pith_number":"pith:EXYO3IG4","schema_version":"1.0","canonical_sha256":"25f0eda0dc089c54f9c1a4261a53fee500cae58385f791be38b0ca5d3f57bc44","source":{"kind":"arxiv","id":"1508.02810","version":2},"attestation_state":"computed","paper":{"title":"Convergence rates of sub-sampled Newton methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Murat A. Erdogdu","submitted_at":"2015-08-12T04:52:58Z","abstract_excerpt":"We consider the problem of minimizing a sum of $n$ functions over a convex parameter set $\\mathcal{C} \\subset \\mathbb{R}^p$ where $n\\gg p\\gg 1$. In this regime, algorithms which utilize sub-sampling techniques are known to be effective. In this paper, we use sub-sampling techniques together with low-rank approximation to design a new randomized batch algorithm which possesses comparable convergence rate to Newton's method, yet has much smaller per-iteration cost. The proposed algorithm is robust in terms of starting point and step size, and enjoys a composite convergence rate, namely, quadrati"},"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":"1508.02810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-08-12T04:52:58Z","cross_cats_sorted":[],"title_canon_sha256":"23efcfaed23af7010f6c7766bff84dd3f87f22b6404a02238d97d5fef2bc5d95","abstract_canon_sha256":"952b2893b4756f934b52fe68b88129f8d70cb69cf2497a22d1477f4e52be04f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:26.215771Z","signature_b64":"cjfJMGm4B6lcGp2nTrJ8EKIt9sfl+Ph9adbOjh3yaguDL8h4cGkMb/3WaMwU6EAuJz0LbNPTWCCB9zMC8MojCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25f0eda0dc089c54f9c1a4261a53fee500cae58385f791be38b0ca5d3f57bc44","last_reissued_at":"2026-05-18T01:25:26.215106Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:26.215106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence rates of sub-sampled Newton methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Murat A. Erdogdu","submitted_at":"2015-08-12T04:52:58Z","abstract_excerpt":"We consider the problem of minimizing a sum of $n$ functions over a convex parameter set $\\mathcal{C} \\subset \\mathbb{R}^p$ where $n\\gg p\\gg 1$. In this regime, algorithms which utilize sub-sampling techniques are known to be effective. In this paper, we use sub-sampling techniques together with low-rank approximation to design a new randomized batch algorithm which possesses comparable convergence rate to Newton's method, yet has much smaller per-iteration cost. The proposed algorithm is robust in terms of starting point and step size, and enjoys a composite convergence rate, namely, quadrati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02810","kind":"arxiv","version":2},"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":"1508.02810","created_at":"2026-05-18T01:25:26.215198+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.02810v2","created_at":"2026-05-18T01:25:26.215198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02810","created_at":"2026-05-18T01:25:26.215198+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXYO3IG4BCOF","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXYO3IG4BCOFJ6OB","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXYO3IG4","created_at":"2026-05-18T12:29:19.899920+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/EXYO3IG4BCOFJ6OBUQTBUU764U","json":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U.json","graph_json":"https://pith.science/api/pith-number/EXYO3IG4BCOFJ6OBUQTBUU764U/graph.json","events_json":"https://pith.science/api/pith-number/EXYO3IG4BCOFJ6OBUQTBUU764U/events.json","paper":"https://pith.science/paper/EXYO3IG4"},"agent_actions":{"view_html":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U","download_json":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U.json","view_paper":"https://pith.science/paper/EXYO3IG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.02810&json=true","fetch_graph":"https://pith.science/api/pith-number/EXYO3IG4BCOFJ6OBUQTBUU764U/graph.json","fetch_events":"https://pith.science/api/pith-number/EXYO3IG4BCOFJ6OBUQTBUU764U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U/action/storage_attestation","attest_author":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U/action/author_attestation","sign_citation":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U/action/citation_signature","submit_replication":"https://pith.science/pith/EXYO3IG4BCOFJ6OBUQTBUU764U/action/replication_record"}},"created_at":"2026-05-18T01:25:26.215198+00:00","updated_at":"2026-05-18T01:25:26.215198+00:00"}