{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:X2DPYUYOCSDHM3YJOXGXBR562T","short_pith_number":"pith:X2DPYUYO","schema_version":"1.0","canonical_sha256":"be86fc530e1486766f0975cd70c7bed4c0d9fe1d472ee6f85f2e2eb1db259997","source":{"kind":"arxiv","id":"2010.04091","version":1},"attestation_state":"computed","paper":{"title":"Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ping-Chun Hsieh, P. R. Kumar, Xi Liu, Yu-Heng Hung","submitted_at":"2020-10-08T16:17:53Z","abstract_excerpt":"Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized linear bandits problems. We develop novel index policies that we prove achieve order-optimality, and show that they achieve empirical performance competitive with the state-of-the-art benchmark methods in extensive experiments. The new policies achieve this with low computation time per pull for linear bandits, and thereby resulting in both favorable regret as "},"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":"2010.04091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T16:17:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0b985595a49f23c207bd746b2e55776a2e8165967a8d79e168ddce9fab79ff81","abstract_canon_sha256":"1018d04055db6c85aabae60d1f54be0be7458a7a9ccf7027d0cf66809dc2e362"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:26.851894Z","signature_b64":"dA8qj/ZscbZ/aorvutsIJQG50AQ/gfgIynfGxn0bI362KFcAk7NO3ipC9qav0Ihp+nOl4V5Vmj4IInypJLd5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be86fc530e1486766f0975cd70c7bed4c0d9fe1d472ee6f85f2e2eb1db259997","last_reissued_at":"2026-07-05T01:41:26.851480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:26.851480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ping-Chun Hsieh, P. R. Kumar, Xi Liu, Yu-Heng Hung","submitted_at":"2020-10-08T16:17:53Z","abstract_excerpt":"Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized linear bandits problems. We develop novel index policies that we prove achieve order-optimality, and show that they achieve empirical performance competitive with the state-of-the-art benchmark methods in extensive experiments. The new policies achieve this with low computation time per pull for linear bandits, and thereby resulting in both favorable regret as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04091","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.04091/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":"2010.04091","created_at":"2026-07-05T01:41:26.851542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04091v1","created_at":"2026-07-05T01:41:26.851542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04091","created_at":"2026-07-05T01:41:26.851542+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2DPYUYOCSDH","created_at":"2026-07-05T01:41:26.851542+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2DPYUYOCSDHM3YJ","created_at":"2026-07-05T01:41:26.851542+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2DPYUYO","created_at":"2026-07-05T01:41:26.851542+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/X2DPYUYOCSDHM3YJOXGXBR562T","json":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T.json","graph_json":"https://pith.science/api/pith-number/X2DPYUYOCSDHM3YJOXGXBR562T/graph.json","events_json":"https://pith.science/api/pith-number/X2DPYUYOCSDHM3YJOXGXBR562T/events.json","paper":"https://pith.science/paper/X2DPYUYO"},"agent_actions":{"view_html":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T","download_json":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T.json","view_paper":"https://pith.science/paper/X2DPYUYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04091&json=true","fetch_graph":"https://pith.science/api/pith-number/X2DPYUYOCSDHM3YJOXGXBR562T/graph.json","fetch_events":"https://pith.science/api/pith-number/X2DPYUYOCSDHM3YJOXGXBR562T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T/action/storage_attestation","attest_author":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T/action/author_attestation","sign_citation":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T/action/citation_signature","submit_replication":"https://pith.science/pith/X2DPYUYOCSDHM3YJOXGXBR562T/action/replication_record"}},"created_at":"2026-07-05T01:41:26.851542+00:00","updated_at":"2026-07-05T01:41:26.851542+00:00"}