{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U7V3WTYFMEIBYHLLF3VN7DHPRW","short_pith_number":"pith:U7V3WTYF","schema_version":"1.0","canonical_sha256":"a7ebbb4f0561101c1d6b2eeadf8cef8daa482f206f098d24a987b2471cfd0db3","source":{"kind":"arxiv","id":"1804.06500","version":2},"attestation_state":"computed","paper":{"title":"Two-Player Games for Efficient Non-Convex Constrained Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Cotter, Heinrich Jiang, Karthik Sridharan","submitted_at":"2018-04-17T23:13:28Z","abstract_excerpt":"In recent years, constrained optimization has become increasingly relevant to the machine learning community, with applications including Neyman-Pearson classification, robust optimization, and fair machine learning. A natural approach to constrained optimization is to optimize the Lagrangian, but this is not guaranteed to work in the non-convex setting, and, if using a first-order method, cannot cope with non-differentiable constraints (e.g. constraints on rates or proportions).\n  The Lagrangian can be interpreted as a two-player game played between a player who seeks to optimize over the mod"},"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":"1804.06500","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-17T23:13:28Z","cross_cats_sorted":["cs.GT","math.OC","stat.ML"],"title_canon_sha256":"c290a59a1ab3079688478b161d78a03e1147e8bd1e365bde1bc7385ef539b4f7","abstract_canon_sha256":"e20241223c98022fdc79aee9009c20b302e6e1745eeedb886ad6af29971717df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:30.084012Z","signature_b64":"oic/l5HHEa3gP0DpeT5QXPGByc36jeYK44s/8VXeN60uFeva1v7W8K/Gl+BUjMrdeWcaAIcz0cdf3kPf6j2NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7ebbb4f0561101c1d6b2eeadf8cef8daa482f206f098d24a987b2471cfd0db3","last_reissued_at":"2026-05-18T00:04:30.083472Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:30.083472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two-Player Games for Efficient Non-Convex Constrained Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Cotter, Heinrich Jiang, Karthik Sridharan","submitted_at":"2018-04-17T23:13:28Z","abstract_excerpt":"In recent years, constrained optimization has become increasingly relevant to the machine learning community, with applications including Neyman-Pearson classification, robust optimization, and fair machine learning. A natural approach to constrained optimization is to optimize the Lagrangian, but this is not guaranteed to work in the non-convex setting, and, if using a first-order method, cannot cope with non-differentiable constraints (e.g. constraints on rates or proportions).\n  The Lagrangian can be interpreted as a two-player game played between a player who seeks to optimize over the mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06500","kind":"arxiv","version":2},"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":"1804.06500","created_at":"2026-05-18T00:04:30.083559+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06500v2","created_at":"2026-05-18T00:04:30.083559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06500","created_at":"2026-05-18T00:04:30.083559+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7V3WTYFMEIB","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7V3WTYFMEIBYHLL","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7V3WTYF","created_at":"2026-05-18T12:32:56.356000+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/U7V3WTYFMEIBYHLLF3VN7DHPRW","json":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW.json","graph_json":"https://pith.science/api/pith-number/U7V3WTYFMEIBYHLLF3VN7DHPRW/graph.json","events_json":"https://pith.science/api/pith-number/U7V3WTYFMEIBYHLLF3VN7DHPRW/events.json","paper":"https://pith.science/paper/U7V3WTYF"},"agent_actions":{"view_html":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW","download_json":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW.json","view_paper":"https://pith.science/paper/U7V3WTYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06500&json=true","fetch_graph":"https://pith.science/api/pith-number/U7V3WTYFMEIBYHLLF3VN7DHPRW/graph.json","fetch_events":"https://pith.science/api/pith-number/U7V3WTYFMEIBYHLLF3VN7DHPRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW/action/storage_attestation","attest_author":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW/action/author_attestation","sign_citation":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW/action/citation_signature","submit_replication":"https://pith.science/pith/U7V3WTYFMEIBYHLLF3VN7DHPRW/action/replication_record"}},"created_at":"2026-05-18T00:04:30.083559+00:00","updated_at":"2026-05-18T00:04:30.083559+00:00"}