{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GGO6KTDXZNMUTPXPT7CAMDURE5","short_pith_number":"pith:GGO6KTDX","schema_version":"1.0","canonical_sha256":"319de54c77cb5949beef9fc4060e912755287d275c0ec21c34d868077d49a682","source":{"kind":"arxiv","id":"1902.03046","version":3},"attestation_state":"computed","paper":{"title":"Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alessandro Rudi (PSL, Dmitrii Ostrovskii (PSL, Francis Bach (PSL, SIERRA), Ulysse Marteau-Ferey (PSL","submitted_at":"2019-02-08T12:18:05Z","abstract_excerpt":"We consider learning methods based on the regularization of a convex empirical risk by a squared Hilbertian norm, a setting that includes linear predictors and non-linear predictors through positive-definite kernels. In order to go beyond the generic analysis leading to convergence rates of the excess risk as $O(1/\\sqrt{n})$ from $n$ observations, we assume that the individual losses are self-concordant, that is, their third-order derivatives are bounded by their second-order derivatives. This setting includes least-squares, as well as all generalized linear models such as logistic and softmax"},"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":"1902.03046","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T12:18:05Z","cross_cats_sorted":["cs.AI","math.ST","stat.TH"],"title_canon_sha256":"d6c40fe2d59ec2f6f8da654550918f5b66fb7b94a546bef4fe089aafaec5f8c0","abstract_canon_sha256":"c8f4cf8a11d27f613cb28f0c220117af4e57b52cf24b793c9f8e7e1b227556ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:03.486603Z","signature_b64":"bT0kGf7+fAqTAaMiAQj3W3Y+xCJJQ0+n7yAuCmDM82c9UmW2Dux7cCZ+0IBvcxUbSLEDtqr2y25eM+VTZpvHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"319de54c77cb5949beef9fc4060e912755287d275c0ec21c34d868077d49a682","last_reissued_at":"2026-05-17T23:43:03.486078Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:03.486078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alessandro Rudi (PSL, Dmitrii Ostrovskii (PSL, Francis Bach (PSL, SIERRA), Ulysse Marteau-Ferey (PSL","submitted_at":"2019-02-08T12:18:05Z","abstract_excerpt":"We consider learning methods based on the regularization of a convex empirical risk by a squared Hilbertian norm, a setting that includes linear predictors and non-linear predictors through positive-definite kernels. In order to go beyond the generic analysis leading to convergence rates of the excess risk as $O(1/\\sqrt{n})$ from $n$ observations, we assume that the individual losses are self-concordant, that is, their third-order derivatives are bounded by their second-order derivatives. This setting includes least-squares, as well as all generalized linear models such as logistic and softmax"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03046","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":"1902.03046","created_at":"2026-05-17T23:43:03.486154+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.03046v3","created_at":"2026-05-17T23:43:03.486154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03046","created_at":"2026-05-17T23:43:03.486154+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGO6KTDXZNMU","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGO6KTDXZNMUTPXP","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGO6KTDX","created_at":"2026-05-18T12:33:18.533446+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/GGO6KTDXZNMUTPXPT7CAMDURE5","json":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5.json","graph_json":"https://pith.science/api/pith-number/GGO6KTDXZNMUTPXPT7CAMDURE5/graph.json","events_json":"https://pith.science/api/pith-number/GGO6KTDXZNMUTPXPT7CAMDURE5/events.json","paper":"https://pith.science/paper/GGO6KTDX"},"agent_actions":{"view_html":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5","download_json":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5.json","view_paper":"https://pith.science/paper/GGO6KTDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.03046&json=true","fetch_graph":"https://pith.science/api/pith-number/GGO6KTDXZNMUTPXPT7CAMDURE5/graph.json","fetch_events":"https://pith.science/api/pith-number/GGO6KTDXZNMUTPXPT7CAMDURE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5/action/storage_attestation","attest_author":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5/action/author_attestation","sign_citation":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5/action/citation_signature","submit_replication":"https://pith.science/pith/GGO6KTDXZNMUTPXPT7CAMDURE5/action/replication_record"}},"created_at":"2026-05-17T23:43:03.486154+00:00","updated_at":"2026-05-17T23:43:03.486154+00:00"}