{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:GNF2PV7MYGNK2IJ5MSTECHTI6P","short_pith_number":"pith:GNF2PV7M","schema_version":"1.0","canonical_sha256":"334ba7d7ecc19aad213d64a6411e68f3ca22d9cb395ec0a3305d9d8883590913","source":{"kind":"arxiv","id":"1311.2547","version":4},"attestation_state":"computed","paper":{"title":"Learning Mixtures of Linear Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Montanari, Stratis Ioannidis, Yuekai Sun","submitted_at":"2013-11-11T19:50:51Z","abstract_excerpt":"We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We develop a simple method based on spectral techniques and a `mirroring' trick, that discovers the subspace spanned by the classifiers' parameter vectors. Under a probabilistic assumption on the feature vector distribution, we prove that this approach has nearly optimal statistical efficiency."},"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":"1311.2547","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-11-11T19:50:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a2f97b7169c5d1ccab2bdc2376f5924c4c980ae04d6997f7a033347e4b8a804f","abstract_canon_sha256":"859ae4d95766161b8d6f90ec784d581fbdc30bce90fefc822df4d5806601bd0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:46:13.014165Z","signature_b64":"btC6BaQEnnetyd13lebiYotU6KAZQJAF0YiONyZcddWpqpXIUYgeH6Eweku3VP3ElHfQkADnJHEsHTSBOCDnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"334ba7d7ecc19aad213d64a6411e68f3ca22d9cb395ec0a3305d9d8883590913","last_reissued_at":"2026-05-18T02:46:13.013457Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:46:13.013457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Mixtures of Linear Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Montanari, Stratis Ioannidis, Yuekai Sun","submitted_at":"2013-11-11T19:50:51Z","abstract_excerpt":"We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We develop a simple method based on spectral techniques and a `mirroring' trick, that discovers the subspace spanned by the classifiers' parameter vectors. Under a probabilistic assumption on the feature vector distribution, we prove that this approach has nearly optimal statistical efficiency."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.2547","kind":"arxiv","version":4},"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":"1311.2547","created_at":"2026-05-18T02:46:13.013562+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.2547v4","created_at":"2026-05-18T02:46:13.013562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.2547","created_at":"2026-05-18T02:46:13.013562+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNF2PV7MYGNK","created_at":"2026-05-18T12:27:45.050594+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNF2PV7MYGNK2IJ5","created_at":"2026-05-18T12:27:45.050594+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNF2PV7M","created_at":"2026-05-18T12:27:45.050594+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/GNF2PV7MYGNK2IJ5MSTECHTI6P","json":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P.json","graph_json":"https://pith.science/api/pith-number/GNF2PV7MYGNK2IJ5MSTECHTI6P/graph.json","events_json":"https://pith.science/api/pith-number/GNF2PV7MYGNK2IJ5MSTECHTI6P/events.json","paper":"https://pith.science/paper/GNF2PV7M"},"agent_actions":{"view_html":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P","download_json":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P.json","view_paper":"https://pith.science/paper/GNF2PV7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.2547&json=true","fetch_graph":"https://pith.science/api/pith-number/GNF2PV7MYGNK2IJ5MSTECHTI6P/graph.json","fetch_events":"https://pith.science/api/pith-number/GNF2PV7MYGNK2IJ5MSTECHTI6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P/action/storage_attestation","attest_author":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P/action/author_attestation","sign_citation":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P/action/citation_signature","submit_replication":"https://pith.science/pith/GNF2PV7MYGNK2IJ5MSTECHTI6P/action/replication_record"}},"created_at":"2026-05-18T02:46:13.013562+00:00","updated_at":"2026-05-18T02:46:13.013562+00:00"}