{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:F22FHLQR3YUNDZ7AJNAVZOMALV","short_pith_number":"pith:F22FHLQR","schema_version":"1.0","canonical_sha256":"2eb453ae11de28d1e7e04b415cb9805d47292efa06e19af7a3b4f6d72f76c1d3","source":{"kind":"arxiv","id":"1711.03591","version":1},"attestation_state":"computed","paper":{"title":"Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, K. P. Naveen, Nandan Sudarsanam, Subhojyoti Mukherjee","submitted_at":"2017-11-09T20:36:21Z","abstract_excerpt":"We propose a novel variant of the UCB algorithm (referred to as Efficient-UCB-Variance (EUCBV)) for minimizing cumulative regret in the stochastic multi-armed bandit (MAB) setting. EUCBV incorporates the arm elimination strategy proposed in UCB-Improved \\citep{auer2010ucb}, while taking into account the variance estimates to compute the arms' confidence bounds, similar to UCBV \\citep{audibert2009exploration}. Through a theoretical analysis we establish that EUCBV incurs a \\emph{gap-dependent} regret bound of {\\scriptsize $O\\left( \\dfrac{K\\sigma^2_{\\max} \\log (T\\Delta^2 /K)}{\\Delta}\\right)$} af"},"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":"1711.03591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-09T20:36:21Z","cross_cats_sorted":[],"title_canon_sha256":"38da016d76ffaaedab1c24f2234da345c97e4628b016db8ff227acc35dd0af43","abstract_canon_sha256":"f7c11042dc5f32675cd23d981a2a481a90364cc14ef0063d421d45ce08b8671b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:00.277846Z","signature_b64":"b4ArB9wUfFeZx/jh2my05sO1rYgx8sPxUI1Nw0EFVc2ErG3o21fkzPrKaF4kSZGayAc1VgAo1uw0ADGe+bmHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eb453ae11de28d1e7e04b415cb9805d47292efa06e19af7a3b4f6d72f76c1d3","last_reissued_at":"2026-05-18T00:11:00.276842Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:00.276842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, K. P. Naveen, Nandan Sudarsanam, Subhojyoti Mukherjee","submitted_at":"2017-11-09T20:36:21Z","abstract_excerpt":"We propose a novel variant of the UCB algorithm (referred to as Efficient-UCB-Variance (EUCBV)) for minimizing cumulative regret in the stochastic multi-armed bandit (MAB) setting. EUCBV incorporates the arm elimination strategy proposed in UCB-Improved \\citep{auer2010ucb}, while taking into account the variance estimates to compute the arms' confidence bounds, similar to UCBV \\citep{audibert2009exploration}. Through a theoretical analysis we establish that EUCBV incurs a \\emph{gap-dependent} regret bound of {\\scriptsize $O\\left( \\dfrac{K\\sigma^2_{\\max} \\log (T\\Delta^2 /K)}{\\Delta}\\right)$} af"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03591","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":"1711.03591","created_at":"2026-05-18T00:11:00.277140+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.03591v1","created_at":"2026-05-18T00:11:00.277140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03591","created_at":"2026-05-18T00:11:00.277140+00:00"},{"alias_kind":"pith_short_12","alias_value":"F22FHLQR3YUN","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"F22FHLQR3YUNDZ7A","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"F22FHLQR","created_at":"2026-05-18T12:31:12.930513+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":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV","json":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV.json","graph_json":"https://pith.science/api/pith-number/F22FHLQR3YUNDZ7AJNAVZOMALV/graph.json","events_json":"https://pith.science/api/pith-number/F22FHLQR3YUNDZ7AJNAVZOMALV/events.json","paper":"https://pith.science/paper/F22FHLQR"},"agent_actions":{"view_html":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV","download_json":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV.json","view_paper":"https://pith.science/paper/F22FHLQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.03591&json=true","fetch_graph":"https://pith.science/api/pith-number/F22FHLQR3YUNDZ7AJNAVZOMALV/graph.json","fetch_events":"https://pith.science/api/pith-number/F22FHLQR3YUNDZ7AJNAVZOMALV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV/action/storage_attestation","attest_author":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV/action/author_attestation","sign_citation":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV/action/citation_signature","submit_replication":"https://pith.science/pith/F22FHLQR3YUNDZ7AJNAVZOMALV/action/replication_record"}},"created_at":"2026-05-18T00:11:00.277140+00:00","updated_at":"2026-05-18T00:11:00.277140+00:00"}