{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BRWOPG4XGZUQIYIQ5ZQ47XXNUR","short_pith_number":"pith:BRWOPG4X","schema_version":"1.0","canonical_sha256":"0c6ce79b973669046110ee61cfdeeda461fed95ad7e72789ad91b10fa5efb903","source":{"kind":"arxiv","id":"1512.04960","version":2},"attestation_state":"computed","paper":{"title":"A Light Touch for Heavily Constrained SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Cotter, Jan Pfeifer, Maya Gupta","submitted_at":"2015-12-15T21:07:02Z","abstract_excerpt":"Minimizing empirical risk subject to a set of constraints can be a useful strategy for learning restricted classes of functions, such as monotonic functions, submodular functions, classifiers that guarantee a certain class label for some subset of examples, etc. However, these restrictions may result in a very large number of constraints. Projected stochastic gradient descent (SGD) is often the default choice for large-scale optimization in machine learning, but requires a projection after each update. For heavily-constrained objectives, we propose an efficient extension of SGD that stays clos"},"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":"1512.04960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-15T21:07:02Z","cross_cats_sorted":[],"title_canon_sha256":"e894727c98d506fc28641300009394d7f0f9e81cf054400a026620a9761a260e","abstract_canon_sha256":"c6f3a6f826e33036b5a399ffefc5e4c43f61715c96c552d18461a59c077e8f3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:28.878568Z","signature_b64":"pRRf3KNj/uKidCMhT1UZWQ0MgNVsGI49bIFMUHHNYMcbf9XWuc7bQ1h2theGj2ZCATgmnPK9X/JyjupY83boAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c6ce79b973669046110ee61cfdeeda461fed95ad7e72789ad91b10fa5efb903","last_reissued_at":"2026-05-18T01:01:28.878105Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:28.878105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Light Touch for Heavily Constrained SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Cotter, Jan Pfeifer, Maya Gupta","submitted_at":"2015-12-15T21:07:02Z","abstract_excerpt":"Minimizing empirical risk subject to a set of constraints can be a useful strategy for learning restricted classes of functions, such as monotonic functions, submodular functions, classifiers that guarantee a certain class label for some subset of examples, etc. However, these restrictions may result in a very large number of constraints. Projected stochastic gradient descent (SGD) is often the default choice for large-scale optimization in machine learning, but requires a projection after each update. For heavily-constrained objectives, we propose an efficient extension of SGD that stays clos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04960","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":"1512.04960","created_at":"2026-05-18T01:01:28.878168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.04960v2","created_at":"2026-05-18T01:01:28.878168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04960","created_at":"2026-05-18T01:01:28.878168+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRWOPG4XGZUQ","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRWOPG4XGZUQIYIQ","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRWOPG4X","created_at":"2026-05-18T12:29:14.074870+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/BRWOPG4XGZUQIYIQ5ZQ47XXNUR","json":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR.json","graph_json":"https://pith.science/api/pith-number/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/graph.json","events_json":"https://pith.science/api/pith-number/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/events.json","paper":"https://pith.science/paper/BRWOPG4X"},"agent_actions":{"view_html":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR","download_json":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR.json","view_paper":"https://pith.science/paper/BRWOPG4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.04960&json=true","fetch_graph":"https://pith.science/api/pith-number/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/graph.json","fetch_events":"https://pith.science/api/pith-number/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/action/storage_attestation","attest_author":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/action/author_attestation","sign_citation":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/action/citation_signature","submit_replication":"https://pith.science/pith/BRWOPG4XGZUQIYIQ5ZQ47XXNUR/action/replication_record"}},"created_at":"2026-05-18T01:01:28.878168+00:00","updated_at":"2026-05-18T01:01:28.878168+00:00"}