{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NIZRNCP3GPHBDWFOHVDAA6XU7B","short_pith_number":"pith:NIZRNCP3","schema_version":"1.0","canonical_sha256":"6a331689fb33ce11d8ae3d46007af4f84347d2a4577216ae4678d724661232c2","source":{"kind":"arxiv","id":"2206.00099","version":1},"attestation_state":"computed","paper":{"title":"Provably and Practically Efficient Neural Contextual Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qing Zhao, Sattar Vakili, Sudeep Salgia","submitted_at":"2022-05-31T20:16:55Z","abstract_excerpt":"We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions. Under this more general setting, (i) we derive non-asymptotic error bounds on the difference between an overparameterized neural net and its corresponding neural tangent kernel, (ii) we propose an algorithm with a provably sublinear regret bound that is also efficient in the finite regime as demonstrated by empirical studies. The non-asymptotic error bounds may be of broader interest as a tool to establish the "},"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":"2206.00099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-05-31T20:16:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4799afd23d4ce157c5f09af8db7c077697667a4af3696fc1d32df156454a04db","abstract_canon_sha256":"bc19e401bf1f7e2f789fb6dbca8b9e6983e3c18a9a85b19a47fc7bdc306ba133"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:13.000376Z","signature_b64":"jDRRvQJqHjhas45g+tXS4O3iW6iDm0Ul318q3TDkJ/3ySEPfFkyqUwXdrDfUAhdi4ituzwWLyXW8UMtnI4yhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a331689fb33ce11d8ae3d46007af4f84347d2a4577216ae4678d724661232c2","last_reissued_at":"2026-07-05T04:28:12.999995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:12.999995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably and Practically Efficient Neural Contextual Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qing Zhao, Sattar Vakili, Sudeep Salgia","submitted_at":"2022-05-31T20:16:55Z","abstract_excerpt":"We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions. Under this more general setting, (i) we derive non-asymptotic error bounds on the difference between an overparameterized neural net and its corresponding neural tangent kernel, (ii) we propose an algorithm with a provably sublinear regret bound that is also efficient in the finite regime as demonstrated by empirical studies. The non-asymptotic error bounds may be of broader interest as a tool to establish the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00099","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/2206.00099/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":"2206.00099","created_at":"2026-07-05T04:28:13.000051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00099v1","created_at":"2026-07-05T04:28:13.000051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00099","created_at":"2026-07-05T04:28:13.000051+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIZRNCP3GPHB","created_at":"2026-07-05T04:28:13.000051+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIZRNCP3GPHBDWFO","created_at":"2026-07-05T04:28:13.000051+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIZRNCP3","created_at":"2026-07-05T04:28:13.000051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02079","citing_title":"Online Clustering of Dueling Bandits","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B","json":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B.json","graph_json":"https://pith.science/api/pith-number/NIZRNCP3GPHBDWFOHVDAA6XU7B/graph.json","events_json":"https://pith.science/api/pith-number/NIZRNCP3GPHBDWFOHVDAA6XU7B/events.json","paper":"https://pith.science/paper/NIZRNCP3"},"agent_actions":{"view_html":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B","download_json":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B.json","view_paper":"https://pith.science/paper/NIZRNCP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00099&json=true","fetch_graph":"https://pith.science/api/pith-number/NIZRNCP3GPHBDWFOHVDAA6XU7B/graph.json","fetch_events":"https://pith.science/api/pith-number/NIZRNCP3GPHBDWFOHVDAA6XU7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B/action/storage_attestation","attest_author":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B/action/author_attestation","sign_citation":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B/action/citation_signature","submit_replication":"https://pith.science/pith/NIZRNCP3GPHBDWFOHVDAA6XU7B/action/replication_record"}},"created_at":"2026-07-05T04:28:13.000051+00:00","updated_at":"2026-07-05T04:28:13.000051+00:00"}