{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JZH3U3P6UHH7DZ4BWPFXGICVE7","short_pith_number":"pith:JZH3U3P6","schema_version":"1.0","canonical_sha256":"4e4fba6dfea1cff1e781b3cb73205527ca4ddea564542dfbba26c557dfd54cad","source":{"kind":"arxiv","id":"2107.03144","version":2},"attestation_state":"computed","paper":{"title":"Neural Contextual Bandits without Regret","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Parnian Kassraie","submitted_at":"2021-07-07T11:11:34Z","abstract_excerpt":"Contextual bandits are a rich model for sequential decision making given side information, with important applications, e.g., in recommender systems. We propose novel algorithms for contextual bandits harnessing neural networks to approximate the unknown reward function. We resolve the open problem of proving sublinear regret bounds in this setting for general context sequences, considering both fully-connected and convolutional networks. To this end, we first analyze NTK-UCB, a kernelized bandit optimization algorithm employing the Neural Tangent Kernel (NTK), and bound its regret in terms of"},"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":"2107.03144","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-07T11:11:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2cbb91b3e2d4e21c6bd0c5da2d72ae80037a89625f00e2d806562bbccb1d102d","abstract_canon_sha256":"e3fe42bc78dd29ca404450dfeefae6bc9178a63e50614c46c09440a34b2444ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:16.048906Z","signature_b64":"bFxpVsTH3El/y8GlpKz3Gd0Vxm427iUs2bP75yxSIT/0ezkgr+/K5uVz6trhjWOeWHSXqpP1QcLLGCLlFA42Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e4fba6dfea1cff1e781b3cb73205527ca4ddea564542dfbba26c557dfd54cad","last_reissued_at":"2026-07-05T04:00:16.048444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:16.048444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Contextual Bandits without Regret","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Parnian Kassraie","submitted_at":"2021-07-07T11:11:34Z","abstract_excerpt":"Contextual bandits are a rich model for sequential decision making given side information, with important applications, e.g., in recommender systems. We propose novel algorithms for contextual bandits harnessing neural networks to approximate the unknown reward function. We resolve the open problem of proving sublinear regret bounds in this setting for general context sequences, considering both fully-connected and convolutional networks. To this end, we first analyze NTK-UCB, a kernelized bandit optimization algorithm employing the Neural Tangent Kernel (NTK), and bound its regret in terms of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03144","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.03144/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":"2107.03144","created_at":"2026-07-05T04:00:16.048502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03144v2","created_at":"2026-07-05T04:00:16.048502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03144","created_at":"2026-07-05T04:00:16.048502+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZH3U3P6UHH7","created_at":"2026-07-05T04:00:16.048502+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZH3U3P6UHH7DZ4B","created_at":"2026-07-05T04:00:16.048502+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZH3U3P6","created_at":"2026-07-05T04:00:16.048502+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/JZH3U3P6UHH7DZ4BWPFXGICVE7","json":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7.json","graph_json":"https://pith.science/api/pith-number/JZH3U3P6UHH7DZ4BWPFXGICVE7/graph.json","events_json":"https://pith.science/api/pith-number/JZH3U3P6UHH7DZ4BWPFXGICVE7/events.json","paper":"https://pith.science/paper/JZH3U3P6"},"agent_actions":{"view_html":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7","download_json":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7.json","view_paper":"https://pith.science/paper/JZH3U3P6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03144&json=true","fetch_graph":"https://pith.science/api/pith-number/JZH3U3P6UHH7DZ4BWPFXGICVE7/graph.json","fetch_events":"https://pith.science/api/pith-number/JZH3U3P6UHH7DZ4BWPFXGICVE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7/action/storage_attestation","attest_author":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7/action/author_attestation","sign_citation":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7/action/citation_signature","submit_replication":"https://pith.science/pith/JZH3U3P6UHH7DZ4BWPFXGICVE7/action/replication_record"}},"created_at":"2026-07-05T04:00:16.048502+00:00","updated_at":"2026-07-05T04:00:16.048502+00:00"}