{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3RFEKAYMCEAYONSXRYX6AZDHKW","short_pith_number":"pith:3RFEKAYM","schema_version":"1.0","canonical_sha256":"dc4a45030c11018736578e2fe0646755ba1ebae5b28c919db65fa7208d0e28b6","source":{"kind":"arxiv","id":"1906.07611","version":1},"attestation_state":"computed","paper":{"title":"Simple Algorithms for Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Lamperski, Tyler Lekang","submitted_at":"2019-06-18T14:35:10Z","abstract_excerpt":"In this paper, we present simple algorithms for Dueling Bandits. We prove that the algorithms have regret bounds for time horizon T of order O(T^rho ) with 1/2 <= rho <= 3/4, which importantly do not depend on any preference gap between actions, Delta. Dueling Bandits is an important extension of the Multi-Armed Bandit problem, in which the algorithm must select two actions at a time and only receives binary feedback for the duel outcome. This is analogous to comparisons in which the rater can only provide yes/no or better/worse type responses. We compare our simple algorithms to the current s"},"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":"1906.07611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T14:35:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0b7d719fc5b6e6ee770760042833fb6509a01a26fde0dee36f828a1770e280af","abstract_canon_sha256":"d8bba6b221f27b7928fd79b531000d80b829629408834382666c62dd82b082a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:59.724051Z","signature_b64":"vRiLBRU2/93BBiCURO/OLr/GxgKGCPFoA049P19Ob/07x0kINyVTypF5slqrd6bL2pB3QMSthMWAinzxc49HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4a45030c11018736578e2fe0646755ba1ebae5b28c919db65fa7208d0e28b6","last_reissued_at":"2026-05-17T23:42:59.723557Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:59.723557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Algorithms for Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Lamperski, Tyler Lekang","submitted_at":"2019-06-18T14:35:10Z","abstract_excerpt":"In this paper, we present simple algorithms for Dueling Bandits. We prove that the algorithms have regret bounds for time horizon T of order O(T^rho ) with 1/2 <= rho <= 3/4, which importantly do not depend on any preference gap between actions, Delta. Dueling Bandits is an important extension of the Multi-Armed Bandit problem, in which the algorithm must select two actions at a time and only receives binary feedback for the duel outcome. This is analogous to comparisons in which the rater can only provide yes/no or better/worse type responses. We compare our simple algorithms to the current s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07611","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":"1906.07611","created_at":"2026-05-17T23:42:59.723646+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07611v1","created_at":"2026-05-17T23:42:59.723646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07611","created_at":"2026-05-17T23:42:59.723646+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RFEKAYMCEAY","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RFEKAYMCEAYONSX","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RFEKAYM","created_at":"2026-05-18T12:33:10.108867+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/3RFEKAYMCEAYONSXRYX6AZDHKW","json":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW.json","graph_json":"https://pith.science/api/pith-number/3RFEKAYMCEAYONSXRYX6AZDHKW/graph.json","events_json":"https://pith.science/api/pith-number/3RFEKAYMCEAYONSXRYX6AZDHKW/events.json","paper":"https://pith.science/paper/3RFEKAYM"},"agent_actions":{"view_html":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW","download_json":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW.json","view_paper":"https://pith.science/paper/3RFEKAYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07611&json=true","fetch_graph":"https://pith.science/api/pith-number/3RFEKAYMCEAYONSXRYX6AZDHKW/graph.json","fetch_events":"https://pith.science/api/pith-number/3RFEKAYMCEAYONSXRYX6AZDHKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW/action/storage_attestation","attest_author":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW/action/author_attestation","sign_citation":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW/action/citation_signature","submit_replication":"https://pith.science/pith/3RFEKAYMCEAYONSXRYX6AZDHKW/action/replication_record"}},"created_at":"2026-05-17T23:42:59.723646+00:00","updated_at":"2026-05-17T23:42:59.723646+00:00"}