{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MYYVSUR46MICGBAMQIWED5ZD5A","short_pith_number":"pith:MYYVSUR4","schema_version":"1.0","canonical_sha256":"663159523cf31023040c822c41f723e80e4752bdb2565490b03c6adb3c783494","source":{"kind":"arxiv","id":"2012.01780","version":1},"attestation_state":"computed","paper":{"title":"Neural Contextual Bandits with Deep Representation and Shallow Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Handong Zhao, Pan Xu, Quanquan Gu, Zheng Wen","submitted_at":"2020-12-03T09:17:55Z","abstract_excerpt":"We study a general class of contextual bandits, where each context-action pair is associated with a raw feature vector, but the reward generating function is unknown. We propose a novel learning algorithm that transforms the raw feature vector using the last hidden layer of a deep ReLU neural network (deep representation learning), and uses an upper confidence bound (UCB) approach to explore in the last linear layer (shallow exploration). We prove that under standard assumptions, our proposed algorithm achieves $\\tilde{O}(\\sqrt{T})$ finite-time regret, where $T$ is the learning time horizon. C"},"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":"2012.01780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-03T09:17:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9681089ea667b092b3ede979fd60d1d29e866c3c73eb12ea9fa222f6d648f280","abstract_canon_sha256":"0eb15e9b2a8befca97bbf2996df9376b8d6b9741ec3c07328741ee24568b8c5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:50.037634Z","signature_b64":"WXh8xBhkl0P2ghT4xwN4Dj5ctTw+3zm5i/unIzFD/sRaXuQZ380ULR4GgM6KurB2FIVwjZMdP3a9mdscICYTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"663159523cf31023040c822c41f723e80e4752bdb2565490b03c6adb3c783494","last_reissued_at":"2026-07-05T01:56:50.037203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:50.037203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Contextual Bandits with Deep Representation and Shallow Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Handong Zhao, Pan Xu, Quanquan Gu, Zheng Wen","submitted_at":"2020-12-03T09:17:55Z","abstract_excerpt":"We study a general class of contextual bandits, where each context-action pair is associated with a raw feature vector, but the reward generating function is unknown. We propose a novel learning algorithm that transforms the raw feature vector using the last hidden layer of a deep ReLU neural network (deep representation learning), and uses an upper confidence bound (UCB) approach to explore in the last linear layer (shallow exploration). We prove that under standard assumptions, our proposed algorithm achieves $\\tilde{O}(\\sqrt{T})$ finite-time regret, where $T$ is the learning time horizon. C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01780","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/2012.01780/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":"2012.01780","created_at":"2026-07-05T01:56:50.037260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.01780v1","created_at":"2026-07-05T01:56:50.037260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01780","created_at":"2026-07-05T01:56:50.037260+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYYVSUR46MIC","created_at":"2026-07-05T01:56:50.037260+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYYVSUR46MICGBAM","created_at":"2026-07-05T01:56:50.037260+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYYVSUR4","created_at":"2026-07-05T01:56:50.037260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08032","citing_title":"Variational Proximal Policy Optimization","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01080","citing_title":"Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2305.03784","citing_title":"Neural Exploitation and Exploration of Contextual Bandits","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01250","citing_title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A","json":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A.json","graph_json":"https://pith.science/api/pith-number/MYYVSUR46MICGBAMQIWED5ZD5A/graph.json","events_json":"https://pith.science/api/pith-number/MYYVSUR46MICGBAMQIWED5ZD5A/events.json","paper":"https://pith.science/paper/MYYVSUR4"},"agent_actions":{"view_html":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A","download_json":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A.json","view_paper":"https://pith.science/paper/MYYVSUR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.01780&json=true","fetch_graph":"https://pith.science/api/pith-number/MYYVSUR46MICGBAMQIWED5ZD5A/graph.json","fetch_events":"https://pith.science/api/pith-number/MYYVSUR46MICGBAMQIWED5ZD5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A/action/storage_attestation","attest_author":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A/action/author_attestation","sign_citation":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A/action/citation_signature","submit_replication":"https://pith.science/pith/MYYVSUR46MICGBAMQIWED5ZD5A/action/replication_record"}},"created_at":"2026-07-05T01:56:50.037260+00:00","updated_at":"2026-07-05T01:56:50.037260+00:00"}