{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:E2FZRMKQ2WYZVKZDJE4QSSSZZI","short_pith_number":"pith:E2FZRMKQ","schema_version":"1.0","canonical_sha256":"268b98b150d5b19aab234939094a59ca21c0ccbf0a583d3e0966a055bc9f9be5","source":{"kind":"arxiv","id":"1611.10258","version":1},"attestation_state":"computed","paper":{"title":"Reliably Learning the ReLU in Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Klivans, Justin Thaler, Surbhi Goel, Varun Kanade","submitted_at":"2016-11-30T16:42:23Z","abstract_excerpt":"We give the first dimension-efficient algorithms for learning Rectified Linear Units (ReLUs), which are functions of the form $\\mathbf{x} \\mapsto \\max(0, \\mathbf{w} \\cdot \\mathbf{x})$ with $\\mathbf{w} \\in \\mathbb{S}^{n-1}$. Our algorithm works in the challenging Reliable Agnostic learning model of Kalai, Kanade, and Mansour (2009) where the learner is given access to a distribution $\\cal{D}$ on labeled examples but the labeling may be arbitrary. We construct a hypothesis that simultaneously minimizes the false-positive rate and the loss on inputs given positive labels by $\\cal{D}$, for any con"},"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":"1611.10258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-30T16:42:23Z","cross_cats_sorted":["cs.CC","stat.ML"],"title_canon_sha256":"c973faae5b0f68b140add59b03799320b08390d1a600e8459f2bb3969f180e0a","abstract_canon_sha256":"9edc58ecac031746d346ffc49a62c24711117a851590f182cba29977b0b06c04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:54.062237Z","signature_b64":"ZSrjwoF54ExQteodZ+0Tb8FOTXHF3iti2BwbA50k2QcdMEHyvOLXT1in1XyqJep9eOQxmaE2iweYRQmMwWMqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"268b98b150d5b19aab234939094a59ca21c0ccbf0a583d3e0966a055bc9f9be5","last_reissued_at":"2026-05-18T00:55:54.061808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:54.061808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliably Learning the ReLU in Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Klivans, Justin Thaler, Surbhi Goel, Varun Kanade","submitted_at":"2016-11-30T16:42:23Z","abstract_excerpt":"We give the first dimension-efficient algorithms for learning Rectified Linear Units (ReLUs), which are functions of the form $\\mathbf{x} \\mapsto \\max(0, \\mathbf{w} \\cdot \\mathbf{x})$ with $\\mathbf{w} \\in \\mathbb{S}^{n-1}$. Our algorithm works in the challenging Reliable Agnostic learning model of Kalai, Kanade, and Mansour (2009) where the learner is given access to a distribution $\\cal{D}$ on labeled examples but the labeling may be arbitrary. We construct a hypothesis that simultaneously minimizes the false-positive rate and the loss on inputs given positive labels by $\\cal{D}$, for any con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.10258","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":"1611.10258","created_at":"2026-05-18T00:55:54.061873+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.10258v1","created_at":"2026-05-18T00:55:54.061873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.10258","created_at":"2026-05-18T00:55:54.061873+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2FZRMKQ2WYZ","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2FZRMKQ2WYZVKZD","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2FZRMKQ","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2401.01335","citing_title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","ref_index":108,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI","json":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI.json","graph_json":"https://pith.science/api/pith-number/E2FZRMKQ2WYZVKZDJE4QSSSZZI/graph.json","events_json":"https://pith.science/api/pith-number/E2FZRMKQ2WYZVKZDJE4QSSSZZI/events.json","paper":"https://pith.science/paper/E2FZRMKQ"},"agent_actions":{"view_html":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI","download_json":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI.json","view_paper":"https://pith.science/paper/E2FZRMKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.10258&json=true","fetch_graph":"https://pith.science/api/pith-number/E2FZRMKQ2WYZVKZDJE4QSSSZZI/graph.json","fetch_events":"https://pith.science/api/pith-number/E2FZRMKQ2WYZVKZDJE4QSSSZZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI/action/storage_attestation","attest_author":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI/action/author_attestation","sign_citation":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI/action/citation_signature","submit_replication":"https://pith.science/pith/E2FZRMKQ2WYZVKZDJE4QSSSZZI/action/replication_record"}},"created_at":"2026-05-18T00:55:54.061873+00:00","updated_at":"2026-05-18T00:55:54.061873+00:00"}