{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UB5G4WSF5FY6VPXDA2BM2QBYPF","short_pith_number":"pith:UB5G4WSF","schema_version":"1.0","canonical_sha256":"a07a6e5a45e971eabee30682cd403879560deadf1e6b6703f9dc98d97ae15808","source":{"kind":"arxiv","id":"1702.08000","version":2},"attestation_state":"computed","paper":{"title":"Kiefer Wolfowitz Algorithm is Asymptotically Optimal for a Class of Non-Stationary Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Rahul Singh, Taposh Banerjee","submitted_at":"2017-02-26T08:24:11Z","abstract_excerpt":"We consider the problem of designing an allocation rule or an \"online learning algorithm\" for a class of bandit problems in which the set of control actions available at each time $s$ is a convex, compact subset of $\\mathbb{R}^d$. Upon choosing an action $x$ at time $s$, the algorithm obtains a noisy value of the unknown and time-varying function $f_s$ evaluated at $x$. The \"regret\" of an algorithm is the gap between its expected reward, and the reward earned by a strategy which has the knowledge of the function $f_s$ at each time $s$ and hence chooses the action $x_s$ that maximizes $f_s$.\n  "},"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":"1702.08000","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-26T08:24:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7f713129101b03345cc4f2f6286ad8afdb37b80392d5b540c432d3a7367bd4e","abstract_canon_sha256":"8af2afaf544fe271d6bb86c1c2e34b4e6fd1c5010724a68242e0b60edbc9d9ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:06.221729Z","signature_b64":"AtxhNHuOr28cFSoxZdmwt2vke+dlwqLOJvKitVOwRRwPuEaeXWXPaCpbYD9V3oT2JichF6GinsTaCG/jYStMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a07a6e5a45e971eabee30682cd403879560deadf1e6b6703f9dc98d97ae15808","last_reissued_at":"2026-05-18T00:49:06.221174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:06.221174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kiefer Wolfowitz Algorithm is Asymptotically Optimal for a Class of Non-Stationary Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Rahul Singh, Taposh Banerjee","submitted_at":"2017-02-26T08:24:11Z","abstract_excerpt":"We consider the problem of designing an allocation rule or an \"online learning algorithm\" for a class of bandit problems in which the set of control actions available at each time $s$ is a convex, compact subset of $\\mathbb{R}^d$. Upon choosing an action $x$ at time $s$, the algorithm obtains a noisy value of the unknown and time-varying function $f_s$ evaluated at $x$. The \"regret\" of an algorithm is the gap between its expected reward, and the reward earned by a strategy which has the knowledge of the function $f_s$ at each time $s$ and hence chooses the action $x_s$ that maximizes $f_s$.\n  "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08000","kind":"arxiv","version":2},"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":"1702.08000","created_at":"2026-05-18T00:49:06.221258+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08000v2","created_at":"2026-05-18T00:49:06.221258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08000","created_at":"2026-05-18T00:49:06.221258+00:00"},{"alias_kind":"pith_short_12","alias_value":"UB5G4WSF5FY6","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UB5G4WSF5FY6VPXD","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UB5G4WSF","created_at":"2026-05-18T12:31:46.661854+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/UB5G4WSF5FY6VPXDA2BM2QBYPF","json":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF.json","graph_json":"https://pith.science/api/pith-number/UB5G4WSF5FY6VPXDA2BM2QBYPF/graph.json","events_json":"https://pith.science/api/pith-number/UB5G4WSF5FY6VPXDA2BM2QBYPF/events.json","paper":"https://pith.science/paper/UB5G4WSF"},"agent_actions":{"view_html":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF","download_json":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF.json","view_paper":"https://pith.science/paper/UB5G4WSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08000&json=true","fetch_graph":"https://pith.science/api/pith-number/UB5G4WSF5FY6VPXDA2BM2QBYPF/graph.json","fetch_events":"https://pith.science/api/pith-number/UB5G4WSF5FY6VPXDA2BM2QBYPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF/action/storage_attestation","attest_author":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF/action/author_attestation","sign_citation":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF/action/citation_signature","submit_replication":"https://pith.science/pith/UB5G4WSF5FY6VPXDA2BM2QBYPF/action/replication_record"}},"created_at":"2026-05-18T00:49:06.221258+00:00","updated_at":"2026-05-18T00:49:06.221258+00:00"}