{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CY74CAODTSYPNOEXCJ6HB2KFQT","short_pith_number":"pith:CY74CAOD","schema_version":"1.0","canonical_sha256":"163fc101c39cb0f6b897127c70e94584c88d7eec3b9153a71ee0e8a1a2b998bf","source":{"kind":"arxiv","id":"1905.09884","version":4},"attestation_state":"computed","paper":{"title":"Naive Feature Selection: a Nearly Tight Convex Relaxation for Sparse Naive Bayes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre d'Aspremont, Armin Askari, Laurent El Ghaoui","submitted_at":"2019-05-23T19:30:51Z","abstract_excerpt":"Due to its linear complexity, naive Bayes classification remains an attractive supervised learning method, especially in very large-scale settings. We propose a sparse version of naive Bayes, which can be used for feature selection. This leads to a combinatorial maximum-likelihood problem, for which we provide an exact solution in the case of binary data, or a bound in the multinomial case. We prove that our convex relaxation bounds becomes tight as the marginal contribution of additional features decreases, using a priori duality gap bounds dervied from the Shapley-Folkman theorem. We show ho"},"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":"1905.09884","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T19:30:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"78026dc302cd73f39334a94ba5b7d11446e2899589e5872af00b4209a2cd8d01","abstract_canon_sha256":"5e6c39ac9e21a211d75730c11baddc71f74fdd0fdd4f98d50f4eff219206ffba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:10.553897Z","signature_b64":"iEyRXIMkUCq1KyZ1hMyFsBUVoCTu++1ypxngiQILTwgHnP7TO9/uvT4ZWgAvdLRQqhFx/6aqgQFYu92kR0DeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"163fc101c39cb0f6b897127c70e94584c88d7eec3b9153a71ee0e8a1a2b998bf","last_reissued_at":"2026-07-05T10:29:10.553413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:10.553413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Naive Feature Selection: a Nearly Tight Convex Relaxation for Sparse Naive Bayes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre d'Aspremont, Armin Askari, Laurent El Ghaoui","submitted_at":"2019-05-23T19:30:51Z","abstract_excerpt":"Due to its linear complexity, naive Bayes classification remains an attractive supervised learning method, especially in very large-scale settings. We propose a sparse version of naive Bayes, which can be used for feature selection. This leads to a combinatorial maximum-likelihood problem, for which we provide an exact solution in the case of binary data, or a bound in the multinomial case. We prove that our convex relaxation bounds becomes tight as the marginal contribution of additional features decreases, using a priori duality gap bounds dervied from the Shapley-Folkman theorem. We show ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09884","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.09884/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":"1905.09884","created_at":"2026-07-05T10:29:10.553474+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09884v4","created_at":"2026-07-05T10:29:10.553474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09884","created_at":"2026-07-05T10:29:10.553474+00:00"},{"alias_kind":"pith_short_12","alias_value":"CY74CAODTSYP","created_at":"2026-07-05T10:29:10.553474+00:00"},{"alias_kind":"pith_short_16","alias_value":"CY74CAODTSYPNOEX","created_at":"2026-07-05T10:29:10.553474+00:00"},{"alias_kind":"pith_short_8","alias_value":"CY74CAOD","created_at":"2026-07-05T10:29:10.553474+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/CY74CAODTSYPNOEXCJ6HB2KFQT","json":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT.json","graph_json":"https://pith.science/api/pith-number/CY74CAODTSYPNOEXCJ6HB2KFQT/graph.json","events_json":"https://pith.science/api/pith-number/CY74CAODTSYPNOEXCJ6HB2KFQT/events.json","paper":"https://pith.science/paper/CY74CAOD"},"agent_actions":{"view_html":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT","download_json":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT.json","view_paper":"https://pith.science/paper/CY74CAOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09884&json=true","fetch_graph":"https://pith.science/api/pith-number/CY74CAODTSYPNOEXCJ6HB2KFQT/graph.json","fetch_events":"https://pith.science/api/pith-number/CY74CAODTSYPNOEXCJ6HB2KFQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT/action/storage_attestation","attest_author":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT/action/author_attestation","sign_citation":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT/action/citation_signature","submit_replication":"https://pith.science/pith/CY74CAODTSYPNOEXCJ6HB2KFQT/action/replication_record"}},"created_at":"2026-07-05T10:29:10.553474+00:00","updated_at":"2026-07-05T10:29:10.553474+00:00"}