{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AXIVPY6R5WMYJ5DGOCSYJ4IM7E","short_pith_number":"pith:AXIVPY6R","schema_version":"1.0","canonical_sha256":"05d157e3d1ed9984f46670a584f10cf938686366c3591363dd39330c92d5845b","source":{"kind":"arxiv","id":"1805.09793","version":1},"attestation_state":"computed","paper":{"title":"New Insights into Bootstrapping for Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anup Rao, Branislav Kveton, Mark Schmidt, Sharan Vaswani, Yasin Abbasi-Yadkori, Zheng Wen","submitted_at":"2018-05-24T17:37:17Z","abstract_excerpt":"We investigate the use of bootstrapping in the bandit setting. We first show that the commonly used non-parametric bootstrapping (NPB) procedure can be provably inefficient and establish a near-linear lower bound on the regret incurred by it under the bandit model with Bernoulli rewards. We show that NPB with an appropriate amount of forced exploration can result in sub-linear albeit sub-optimal regret. As an alternative to NPB, we propose a weighted bootstrapping (WB) procedure. For Bernoulli rewards, WB with multiplicative exponential weights is mathematically equivalent to Thompson sampling"},"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":"1805.09793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T17:37:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8132170bd946336b257cd70cd69e4a709ed71915d9dedb043d6a210aa0ff1b56","abstract_canon_sha256":"55d2e96781765752bab393c37f025ae001e9f8e152aa1f27b8f25e40e88288b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:02.837173Z","signature_b64":"/0IlDYO3bnBokUqu6wBuBsL3KtSNIlB0U2Iwmj+cPtY/Wcn8Lww78StJBgEPSqMxPvJy7LANZ5yHOLyltNdKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05d157e3d1ed9984f46670a584f10cf938686366c3591363dd39330c92d5845b","last_reissued_at":"2026-05-18T00:15:02.835952Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:02.835952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"New Insights into Bootstrapping for Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anup Rao, Branislav Kveton, Mark Schmidt, Sharan Vaswani, Yasin Abbasi-Yadkori, Zheng Wen","submitted_at":"2018-05-24T17:37:17Z","abstract_excerpt":"We investigate the use of bootstrapping in the bandit setting. We first show that the commonly used non-parametric bootstrapping (NPB) procedure can be provably inefficient and establish a near-linear lower bound on the regret incurred by it under the bandit model with Bernoulli rewards. We show that NPB with an appropriate amount of forced exploration can result in sub-linear albeit sub-optimal regret. As an alternative to NPB, we propose a weighted bootstrapping (WB) procedure. For Bernoulli rewards, WB with multiplicative exponential weights is mathematically equivalent to Thompson sampling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09793","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":"1805.09793","created_at":"2026-05-18T00:15:02.836469+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09793v1","created_at":"2026-05-18T00:15:02.836469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09793","created_at":"2026-05-18T00:15:02.836469+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXIVPY6R5WMY","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXIVPY6R5WMYJ5DG","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXIVPY6R","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2105.09232","citing_title":"Diffusion Approximations for Thompson Sampling in the Small Gap Regime","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E","json":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E.json","graph_json":"https://pith.science/api/pith-number/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/graph.json","events_json":"https://pith.science/api/pith-number/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/events.json","paper":"https://pith.science/paper/AXIVPY6R"},"agent_actions":{"view_html":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E","download_json":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E.json","view_paper":"https://pith.science/paper/AXIVPY6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09793&json=true","fetch_graph":"https://pith.science/api/pith-number/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/graph.json","fetch_events":"https://pith.science/api/pith-number/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/action/storage_attestation","attest_author":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/action/author_attestation","sign_citation":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/action/citation_signature","submit_replication":"https://pith.science/pith/AXIVPY6R5WMYJ5DGOCSYJ4IM7E/action/replication_record"}},"created_at":"2026-05-18T00:15:02.836469+00:00","updated_at":"2026-05-18T00:15:02.836469+00:00"}