{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LMGFO6OKF6WYV3R3AFL5RE64O6","short_pith_number":"pith:LMGFO6OK","schema_version":"1.0","canonical_sha256":"5b0c5779ca2fad8aee3b0157d893dc77b08a379ae7250a603cdb0b86445b85ec","source":{"kind":"arxiv","id":"1706.01383","version":1},"attestation_state":"computed","paper":{"title":"Sparse Stochastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claire Vernade, Joon Kwon, Vianney Perchet","submitted_at":"2017-06-05T15:46:52Z","abstract_excerpt":"In the classical multi-armed bandit problem, d arms are available to the decision maker who pulls them sequentially in order to maximize his cumulative reward. Guarantees can be obtained on a relative quantity called regret, which scales linearly with d (or with sqrt(d) in the minimax sense). We here consider the sparse case of this classical problem in the sense that only a small number of arms, namely s < d, have a positive expected reward. We are able to leverage this additional assumption to provide an algorithm whose regret scales with s instead of d. Moreover, we prove that this algorith"},"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":"1706.01383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-05T15:46:52Z","cross_cats_sorted":[],"title_canon_sha256":"31778f543ca5b2f46ab39e382f492cbb53516781d732e1dd21dfa7b4e5902ce8","abstract_canon_sha256":"f00077217934f728a5486c9eca20a5ffe10fdc030e1204a2214c8a5e2e046526"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:03.714654Z","signature_b64":"hvwyqZmtaZWU2drV5VhARkmxkOnzc0+mTmJP2xhTTPq83DgYgV39N/DH3JepBqaJRYz7ARRs0zQ74vs+c5N0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b0c5779ca2fad8aee3b0157d893dc77b08a379ae7250a603cdb0b86445b85ec","last_reissued_at":"2026-05-18T00:43:03.714149Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:03.714149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Stochastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claire Vernade, Joon Kwon, Vianney Perchet","submitted_at":"2017-06-05T15:46:52Z","abstract_excerpt":"In the classical multi-armed bandit problem, d arms are available to the decision maker who pulls them sequentially in order to maximize his cumulative reward. Guarantees can be obtained on a relative quantity called regret, which scales linearly with d (or with sqrt(d) in the minimax sense). We here consider the sparse case of this classical problem in the sense that only a small number of arms, namely s < d, have a positive expected reward. We are able to leverage this additional assumption to provide an algorithm whose regret scales with s instead of d. Moreover, we prove that this algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01383","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":"1706.01383","created_at":"2026-05-18T00:43:03.714223+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01383v1","created_at":"2026-05-18T00:43:03.714223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01383","created_at":"2026-05-18T00:43:03.714223+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMGFO6OKF6WY","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMGFO6OKF6WYV3R3","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMGFO6OK","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13738","citing_title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6","json":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6.json","graph_json":"https://pith.science/api/pith-number/LMGFO6OKF6WYV3R3AFL5RE64O6/graph.json","events_json":"https://pith.science/api/pith-number/LMGFO6OKF6WYV3R3AFL5RE64O6/events.json","paper":"https://pith.science/paper/LMGFO6OK"},"agent_actions":{"view_html":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6","download_json":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6.json","view_paper":"https://pith.science/paper/LMGFO6OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01383&json=true","fetch_graph":"https://pith.science/api/pith-number/LMGFO6OKF6WYV3R3AFL5RE64O6/graph.json","fetch_events":"https://pith.science/api/pith-number/LMGFO6OKF6WYV3R3AFL5RE64O6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6/action/storage_attestation","attest_author":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6/action/author_attestation","sign_citation":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6/action/citation_signature","submit_replication":"https://pith.science/pith/LMGFO6OKF6WYV3R3AFL5RE64O6/action/replication_record"}},"created_at":"2026-05-18T00:43:03.714223+00:00","updated_at":"2026-05-18T00:43:03.714223+00:00"}