{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:5JS75PXTIGPZ3ML3DDQYQU4OVJ","short_pith_number":"pith:5JS75PXT","schema_version":"1.0","canonical_sha256":"ea65febef3419f9db17b18e188538eaa7296cdd26d933441b08530b025bcb02b","source":{"kind":"arxiv","id":"1601.03855","version":1},"attestation_state":"computed","paper":{"title":"A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"D), Fabrice Cl\\'erot (FT R, Pratik Gajane, Tanguy Urvoy","submitted_at":"2016-01-15T09:50:07Z","abstract_excerpt":"We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms. We propose a new algorithm called Relative Exponential-weight algorithm for Exploration and Exploitation (REX3) to handle the adversarial utility-based formulation of this problem. This algorithm is a non-trivial extension of the Exponential-weight algorithm for Exploration and Exploitation (EXP3) algorithm. We prove a finite time expected regret upper bound of order O(sqrt(K ln(K)T)) for this a"},"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":"1601.03855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-01-15T09:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"6ad6e05746de64cf3589005fcead484c0f851b6ac4e0c88c261eed1f1df2b6a8","abstract_canon_sha256":"f8edf407023eae8b2fd8a822817c7bbcb9ec55863eda7353ee36f832c120d365"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:49.843915Z","signature_b64":"FOSDMfERvQ09DFKLu9dU73Ha7EcBGMIY3il96dWG27dBVJfU68nf0b9QbFZiBRYmFuIljylO8s+RYMWOBdiXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea65febef3419f9db17b18e188538eaa7296cdd26d933441b08530b025bcb02b","last_reissued_at":"2026-05-18T01:22:49.843344Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:49.843344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"D), Fabrice Cl\\'erot (FT R, Pratik Gajane, Tanguy Urvoy","submitted_at":"2016-01-15T09:50:07Z","abstract_excerpt":"We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms. We propose a new algorithm called Relative Exponential-weight algorithm for Exploration and Exploitation (REX3) to handle the adversarial utility-based formulation of this problem. This algorithm is a non-trivial extension of the Exponential-weight algorithm for Exploration and Exploitation (EXP3) algorithm. We prove a finite time expected regret upper bound of order O(sqrt(K ln(K)T)) for this a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.03855","kind":"arxiv","version":1},"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":"1601.03855","created_at":"2026-05-18T01:22:49.843425+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.03855v1","created_at":"2026-05-18T01:22:49.843425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.03855","created_at":"2026-05-18T01:22:49.843425+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JS75PXTIGPZ","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JS75PXTIGPZ3ML3","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JS75PXT","created_at":"2026-05-18T12:30:01.593930+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/5JS75PXTIGPZ3ML3DDQYQU4OVJ","json":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ.json","graph_json":"https://pith.science/api/pith-number/5JS75PXTIGPZ3ML3DDQYQU4OVJ/graph.json","events_json":"https://pith.science/api/pith-number/5JS75PXTIGPZ3ML3DDQYQU4OVJ/events.json","paper":"https://pith.science/paper/5JS75PXT"},"agent_actions":{"view_html":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ","download_json":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ.json","view_paper":"https://pith.science/paper/5JS75PXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.03855&json=true","fetch_graph":"https://pith.science/api/pith-number/5JS75PXTIGPZ3ML3DDQYQU4OVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5JS75PXTIGPZ3ML3DDQYQU4OVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ/action/storage_attestation","attest_author":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ/action/author_attestation","sign_citation":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ/action/citation_signature","submit_replication":"https://pith.science/pith/5JS75PXTIGPZ3ML3DDQYQU4OVJ/action/replication_record"}},"created_at":"2026-05-18T01:22:49.843425+00:00","updated_at":"2026-05-18T01:22:49.843425+00:00"}