{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:RVFCPJNP7YOTCBSZJJ2RO62O26","short_pith_number":"pith:RVFCPJNP","schema_version":"1.0","canonical_sha256":"8d4a27a5affe1d3106594a75177b4ed793fb822f9a380b394b8d4976d6db08c6","source":{"kind":"arxiv","id":"1408.3115","version":4},"attestation_state":"computed","paper":{"title":"On Data Preconditioning for Regularized Loss Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NA","authors_text":"Qihang Lin, Rong Jin, Shenghuo Zhu, Tianbao Yang","submitted_at":"2014-08-13T18:44:18Z","abstract_excerpt":"In this work, we study data preconditioning, a well-known and long-existing technique, for boosting the convergence of first-order methods for regularized loss minimization. It is well understood that the condition number of the problem, i.e., the ratio of the Lipschitz constant to the strong convexity modulus, has a harsh effect on the convergence of the first-order optimization methods. Therefore, minimizing a small regularized loss for achieving good generalization performance, yielding an ill conditioned problem, becomes the bottleneck for big data problems. We provide a theory on data pre"},"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":"1408.3115","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NA","submitted_at":"2014-08-13T18:44:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0134438c477769f61e182f604b42ef1d1aff0ba16b5341fb4b17247ea843628c","abstract_canon_sha256":"9a6428ac7c5216cd757ce05ef1c076c95649cdfc51f4c244ecbe475f352b7610"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:08.386262Z","signature_b64":"J+oQnh+Xner44Z7bQgDOU/eMwckpKnVwQYy64CJaB37LG8ABxJrPD+0ZjCLyrWpEljLfAaDIgzuF/cLFeUftBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4a27a5affe1d3106594a75177b4ed793fb822f9a380b394b8d4976d6db08c6","last_reissued_at":"2026-05-18T01:32:08.385552Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:08.385552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Data Preconditioning for Regularized Loss Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NA","authors_text":"Qihang Lin, Rong Jin, Shenghuo Zhu, Tianbao Yang","submitted_at":"2014-08-13T18:44:18Z","abstract_excerpt":"In this work, we study data preconditioning, a well-known and long-existing technique, for boosting the convergence of first-order methods for regularized loss minimization. It is well understood that the condition number of the problem, i.e., the ratio of the Lipschitz constant to the strong convexity modulus, has a harsh effect on the convergence of the first-order optimization methods. Therefore, minimizing a small regularized loss for achieving good generalization performance, yielding an ill conditioned problem, becomes the bottleneck for big data problems. We provide a theory on data pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.3115","kind":"arxiv","version":4},"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":"1408.3115","created_at":"2026-05-18T01:32:08.385678+00:00"},{"alias_kind":"arxiv_version","alias_value":"1408.3115v4","created_at":"2026-05-18T01:32:08.385678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.3115","created_at":"2026-05-18T01:32:08.385678+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVFCPJNP7YOT","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVFCPJNP7YOTCBSZ","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVFCPJNP","created_at":"2026-05-18T12:28:46.137349+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/RVFCPJNP7YOTCBSZJJ2RO62O26","json":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26.json","graph_json":"https://pith.science/api/pith-number/RVFCPJNP7YOTCBSZJJ2RO62O26/graph.json","events_json":"https://pith.science/api/pith-number/RVFCPJNP7YOTCBSZJJ2RO62O26/events.json","paper":"https://pith.science/paper/RVFCPJNP"},"agent_actions":{"view_html":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26","download_json":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26.json","view_paper":"https://pith.science/paper/RVFCPJNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1408.3115&json=true","fetch_graph":"https://pith.science/api/pith-number/RVFCPJNP7YOTCBSZJJ2RO62O26/graph.json","fetch_events":"https://pith.science/api/pith-number/RVFCPJNP7YOTCBSZJJ2RO62O26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26/action/storage_attestation","attest_author":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26/action/author_attestation","sign_citation":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26/action/citation_signature","submit_replication":"https://pith.science/pith/RVFCPJNP7YOTCBSZJJ2RO62O26/action/replication_record"}},"created_at":"2026-05-18T01:32:08.385678+00:00","updated_at":"2026-05-18T01:32:08.385678+00:00"}