{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:7QOAL2NYFXTH2ZHUYK6SOF2QYA","short_pith_number":"pith:7QOAL2NY","schema_version":"1.0","canonical_sha256":"fc1c05e9b82de67d64f4c2bd271750c03eb59d014df9dbafbe0f4f0325c7bc1a","source":{"kind":"arxiv","id":"1502.06134","version":3},"attestation_state":"computed","paper":{"title":"Learning with Square Loss: Localization through Offset Rademacher Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexander Rakhlin, Karthik Sridharan, Tengyuan Liang","submitted_at":"2015-02-21T19:20:44Z","abstract_excerpt":"We consider regression with square loss and general classes of functions without the boundedness assumption. We introduce a notion of offset Rademacher complexity that provides a transparent way to study localization both in expectation and in high probability. For any (possibly non-convex) class, the excess loss of a two-step estimator is shown to be upper bounded by this offset complexity through a novel geometric inequality. In the convex case, the estimator reduces to an empirical risk minimizer. The method recovers the results of \\citep{RakSriTsy15} for the bounded case while also providi"},"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":"1502.06134","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-21T19:20:44Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"071497f209cb37ff1270d18e53da233cbc6a245c536d9a0d6f6562b898eaf945","abstract_canon_sha256":"6393b465486f9e77d5a3970bef34972910b33cb5930746fab1e986668f8c1418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:44.215608Z","signature_b64":"fn1ERlFIXMrLWKsNXkT4L8UJ+Uxuty2IuLOC7j3YKSOCo9V1SWuR+IEdnct4LYoWbx9EAuhiRhcmRjf5rodWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc1c05e9b82de67d64f4c2bd271750c03eb59d014df9dbafbe0f4f0325c7bc1a","last_reissued_at":"2026-07-05T01:21:44.215177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:44.215177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Square Loss: Localization through Offset Rademacher Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexander Rakhlin, Karthik Sridharan, Tengyuan Liang","submitted_at":"2015-02-21T19:20:44Z","abstract_excerpt":"We consider regression with square loss and general classes of functions without the boundedness assumption. We introduce a notion of offset Rademacher complexity that provides a transparent way to study localization both in expectation and in high probability. For any (possibly non-convex) class, the excess loss of a two-step estimator is shown to be upper bounded by this offset complexity through a novel geometric inequality. In the convex case, the estimator reduces to an empirical risk minimizer. The method recovers the results of \\citep{RakSriTsy15} for the bounded case while also providi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.06134","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1502.06134/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1502.06134","created_at":"2026-07-05T01:21:44.215229+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.06134v3","created_at":"2026-07-05T01:21:44.215229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.06134","created_at":"2026-07-05T01:21:44.215229+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QOAL2NYFXTH","created_at":"2026-07-05T01:21:44.215229+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QOAL2NYFXTH2ZHU","created_at":"2026-07-05T01:21:44.215229+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QOAL2NY","created_at":"2026-07-05T01:21:44.215229+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/7QOAL2NYFXTH2ZHUYK6SOF2QYA","json":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA.json","graph_json":"https://pith.science/api/pith-number/7QOAL2NYFXTH2ZHUYK6SOF2QYA/graph.json","events_json":"https://pith.science/api/pith-number/7QOAL2NYFXTH2ZHUYK6SOF2QYA/events.json","paper":"https://pith.science/paper/7QOAL2NY"},"agent_actions":{"view_html":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA","download_json":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA.json","view_paper":"https://pith.science/paper/7QOAL2NY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.06134&json=true","fetch_graph":"https://pith.science/api/pith-number/7QOAL2NYFXTH2ZHUYK6SOF2QYA/graph.json","fetch_events":"https://pith.science/api/pith-number/7QOAL2NYFXTH2ZHUYK6SOF2QYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA/action/storage_attestation","attest_author":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA/action/author_attestation","sign_citation":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA/action/citation_signature","submit_replication":"https://pith.science/pith/7QOAL2NYFXTH2ZHUYK6SOF2QYA/action/replication_record"}},"created_at":"2026-07-05T01:21:44.215229+00:00","updated_at":"2026-07-05T01:21:44.215229+00:00"}