{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KQXH6RXNLG6POJ6S2XV64ZE7VT","short_pith_number":"pith:KQXH6RXN","schema_version":"1.0","canonical_sha256":"542e7f46ed59bcf727d2d5ebee649faccad29038656beaefe5320dfc5c29995d","source":{"kind":"arxiv","id":"1905.04447","version":1},"attestation_state":"computed","paper":{"title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.DS","authors_text":"Qiuyi Zhang, Yin Tat Lee, Zhao Song","submitted_at":"2019-05-11T04:42:16Z","abstract_excerpt":"Many convex problems in machine learning and computer science share the same form: \\begin{align*} \\min_{x} \\sum_{i} f_i( A_i x + b_i), \\end{align*} where $f_i$ are convex functions on $\\mathbb{R}^{n_i}$ with constant $n_i$, $A_i \\in \\mathbb{R}^{n_i \\times d}$, $b_i \\in \\mathbb{R}^{n_i}$ and $\\sum_i n_i = n$. This problem generalizes linear programming and includes many problems in empirical risk minimization. In this paper, we give an algorithm that runs in time \\begin{align*} O^* ( ( n^{\\omega} + n^{2.5 - \\alpha/2} + n^{2+ 1/6} ) \\log (n / \\delta) ) \\end{align*} where $\\omega$ is the exponent"},"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":"1905.04447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DS","submitted_at":"2019-05-11T04:42:16Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"d5694534e8033a9b8309f6fb2ab31deb182a89bf3812ce5da9bab1798be6c76e","abstract_canon_sha256":"950d3fb8e6800ca4a1edc91c097d35e2c8481397072786b0f662f341c38a6f1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:24.818009Z","signature_b64":"+YKgcGjzjI63kGc9GZKXzHEzxp7mPPTfjaf0TurjKa8S19tEMkgxXr0UTr4PUJH9fVHImcIWAbSy2mGSGbozDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"542e7f46ed59bcf727d2d5ebee649faccad29038656beaefe5320dfc5c29995d","last_reissued_at":"2026-05-17T23:46:24.817377Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:24.817377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.DS","authors_text":"Qiuyi Zhang, Yin Tat Lee, Zhao Song","submitted_at":"2019-05-11T04:42:16Z","abstract_excerpt":"Many convex problems in machine learning and computer science share the same form: \\begin{align*} \\min_{x} \\sum_{i} f_i( A_i x + b_i), \\end{align*} where $f_i$ are convex functions on $\\mathbb{R}^{n_i}$ with constant $n_i$, $A_i \\in \\mathbb{R}^{n_i \\times d}$, $b_i \\in \\mathbb{R}^{n_i}$ and $\\sum_i n_i = n$. This problem generalizes linear programming and includes many problems in empirical risk minimization. In this paper, we give an algorithm that runs in time \\begin{align*} O^* ( ( n^{\\omega} + n^{2.5 - \\alpha/2} + n^{2+ 1/6} ) \\log (n / \\delta) ) \\end{align*} where $\\omega$ is the exponent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04447","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":"1905.04447","created_at":"2026-05-17T23:46:24.817475+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04447v1","created_at":"2026-05-17T23:46:24.817475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04447","created_at":"2026-05-17T23:46:24.817475+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQXH6RXNLG6P","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQXH6RXNLG6POJ6S","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQXH6RXN","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24488","citing_title":"Scalable First-Order Interior Point Trust Region Algorithms for Linearly Constrained Optimization","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT","json":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT.json","graph_json":"https://pith.science/api/pith-number/KQXH6RXNLG6POJ6S2XV64ZE7VT/graph.json","events_json":"https://pith.science/api/pith-number/KQXH6RXNLG6POJ6S2XV64ZE7VT/events.json","paper":"https://pith.science/paper/KQXH6RXN"},"agent_actions":{"view_html":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT","download_json":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT.json","view_paper":"https://pith.science/paper/KQXH6RXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04447&json=true","fetch_graph":"https://pith.science/api/pith-number/KQXH6RXNLG6POJ6S2XV64ZE7VT/graph.json","fetch_events":"https://pith.science/api/pith-number/KQXH6RXNLG6POJ6S2XV64ZE7VT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT/action/storage_attestation","attest_author":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT/action/author_attestation","sign_citation":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT/action/citation_signature","submit_replication":"https://pith.science/pith/KQXH6RXNLG6POJ6S2XV64ZE7VT/action/replication_record"}},"created_at":"2026-05-17T23:46:24.817475+00:00","updated_at":"2026-05-17T23:46:24.817475+00:00"}