{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UG2ZORO5FXKGCOOUOK7FNAJOI6","short_pith_number":"pith:UG2ZORO5","schema_version":"1.0","canonical_sha256":"a1b59745dd2dd46139d472be56812e47b5e49934259d15450e7cb1410777a568","source":{"kind":"arxiv","id":"1902.02244","version":2},"attestation_state":"computed","paper":{"title":"Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alina Beygelzimer, Bal\\'azs Sz\\\"or\\'enyi, Chen-Yu Wei, Chicheng Zhang, D\\'avid P\\'al, Devanathan Thiruvenkatachari","submitted_at":"2019-02-06T15:47:38Z","abstract_excerpt":"We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of $K$ classes and lie in the $d$-dimensional Euclidean space. Previous works have left open the challenge of designing efficient algorithms with finite mistake bounds when the data is linearly separable by a margin $\\gamma$. In this work, we take a first step towards this problem. We consider two notions of linear separability: strong and weak.\n  1. Under the strong linear separability condition, we design an efficient algorithm that achieves a near-optimal mistake "},"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":"1902.02244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-06T15:47:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b196c7b44612eec5dfd0be30da9436338ee5127a8283a97176b9d614c232effb","abstract_canon_sha256":"e90d51504e7bd9becfa1905f148b39df61d340b0ae86fea032d88c685e4d4885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:09.057512Z","signature_b64":"LTxrPMUlb9p97gtNqcw+YGHPFSKW7OPO+cUFDMiivuvL0JI/b00jDrLl/seq0mdskynvAh5JuUX6b6W5n2QWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1b59745dd2dd46139d472be56812e47b5e49934259d15450e7cb1410777a568","last_reissued_at":"2026-05-17T23:43:09.056774Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:09.056774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alina Beygelzimer, Bal\\'azs Sz\\\"or\\'enyi, Chen-Yu Wei, Chicheng Zhang, D\\'avid P\\'al, Devanathan Thiruvenkatachari","submitted_at":"2019-02-06T15:47:38Z","abstract_excerpt":"We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of $K$ classes and lie in the $d$-dimensional Euclidean space. Previous works have left open the challenge of designing efficient algorithms with finite mistake bounds when the data is linearly separable by a margin $\\gamma$. In this work, we take a first step towards this problem. We consider two notions of linear separability: strong and weak.\n  1. Under the strong linear separability condition, we design an efficient algorithm that achieves a near-optimal mistake "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02244","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":"1902.02244","created_at":"2026-05-17T23:43:09.056894+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02244v2","created_at":"2026-05-17T23:43:09.056894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02244","created_at":"2026-05-17T23:43:09.056894+00:00"},{"alias_kind":"pith_short_12","alias_value":"UG2ZORO5FXKG","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UG2ZORO5FXKGCOOU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UG2ZORO5","created_at":"2026-05-18T12:33:30.264802+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/UG2ZORO5FXKGCOOUOK7FNAJOI6","json":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6.json","graph_json":"https://pith.science/api/pith-number/UG2ZORO5FXKGCOOUOK7FNAJOI6/graph.json","events_json":"https://pith.science/api/pith-number/UG2ZORO5FXKGCOOUOK7FNAJOI6/events.json","paper":"https://pith.science/paper/UG2ZORO5"},"agent_actions":{"view_html":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6","download_json":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6.json","view_paper":"https://pith.science/paper/UG2ZORO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02244&json=true","fetch_graph":"https://pith.science/api/pith-number/UG2ZORO5FXKGCOOUOK7FNAJOI6/graph.json","fetch_events":"https://pith.science/api/pith-number/UG2ZORO5FXKGCOOUOK7FNAJOI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6/action/storage_attestation","attest_author":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6/action/author_attestation","sign_citation":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6/action/citation_signature","submit_replication":"https://pith.science/pith/UG2ZORO5FXKGCOOUOK7FNAJOI6/action/replication_record"}},"created_at":"2026-05-17T23:43:09.056894+00:00","updated_at":"2026-05-17T23:43:09.056894+00:00"}