{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2JDHXKAYJWQLMV6FJSH2M5ZAKT","short_pith_number":"pith:2JDHXKAY","schema_version":"1.0","canonical_sha256":"d2467ba8184da0b657c54c8fa6772054fcb519793c13ac6467754da944458d2e","source":{"kind":"arxiv","id":"2506.01250","version":3},"attestation_state":"computed","paper":{"title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT)).","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaemin Park, Jinje Park, Taejin Paik, Youngmin Oh","submitted_at":"2025-06-02T01:58:48Z","abstract_excerpt":"We introduce the first variance-aware algorithms for contextual dueling bandits that leverage shallow exploration strategies with neural networks for nonlinear utility approximation. A key theoretical challenge is the absence of a closed-form estimator, which led prior work to require an extremely large network width $m$ (i.e., $m = \\widetilde{\\Omega}(T^{14})$). We address this constraint with a novel analytical approach that combines iterative self-improvement with spectral analysis. Our analysis significantly reduces the network width requirement to $m = \\widetilde{\\Omega}(T^{6})$, and shows"},"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":"2506.01250","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T01:58:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"935f4f67589a8b5afdac16c0e2762295ed0c7f3cc925a66e226d536209e36e6c","abstract_canon_sha256":"a76a6ed15663fd9eb988b996d144c570cd05051e98f49335d6d8b3ae698d1228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:29.443460Z","signature_b64":"JE8kJRdnwPE1LHiisUb2gRwbrYkHw7UYOjo3Kc14iBsj+7OhHHlgTSpRdrl1eWNS5UCB+lEjh8TYtQALfIgWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2467ba8184da0b657c54c8fa6772054fcb519793c13ac6467754da944458d2e","last_reissued_at":"2026-06-04T01:08:29.442894Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:29.442894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT)).","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaemin Park, Jinje Park, Taejin Paik, Youngmin Oh","submitted_at":"2025-06-02T01:58:48Z","abstract_excerpt":"We introduce the first variance-aware algorithms for contextual dueling bandits that leverage shallow exploration strategies with neural networks for nonlinear utility approximation. A key theoretical challenge is the absence of a closed-form estimator, which led prior work to require an extremely large network width $m$ (i.e., $m = \\widetilde{\\Omega}(T^{14})$). We address this constraint with a novel analytical approach that combines iterative self-improvement with spectral analysis. Our analysis significantly reduces the network width requirement to $m = \\widetilde{\\Omega}(T^{6})$, and shows"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under standard assumptions, our algorithms achieve sublinear cumulative average regret of order O(d sqrt(sum_{t=1}^T sigma_t^2) + sqrt(d T)) for sufficiently wide neural networks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The neural networks must be sufficiently wide to approximate the unknown nonlinear utility functions, and the variance-aware exploration strategy must be effective when computed solely from last-layer gradients without requiring deeper network information.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT)).","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c104f98bf241e905f2687818ee7de2e43023026b31b600f38ec46d3306a09bdb"},"source":{"id":"2506.01250","kind":"arxiv","version":3},"verdict":{"id":"5d7dd0d9-1dd4-48f6-9834-7aab0d65d1c9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T11:26:03.213117Z","strongest_claim":"Under standard assumptions, our algorithms achieve sublinear cumulative average regret of order O(d sqrt(sum_{t=1}^T sigma_t^2) + sqrt(d T)) for sufficiently wide neural networks.","one_line_summary":"Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The neural networks must be sufficiently wide to approximate the unknown nonlinear utility functions, and the variance-aware exploration strategy must be effective when computed solely from last-layer gradients without requiring deeper network information.","pith_extraction_headline":"Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT))."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.01250/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":"2506.01250","created_at":"2026-06-04T01:08:29.442958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01250v3","created_at":"2026-06-04T01:08:29.442958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01250","created_at":"2026-06-04T01:08:29.442958+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JDHXKAYJWQL","created_at":"2026-06-04T01:08:29.442958+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JDHXKAYJWQLMV6F","created_at":"2026-06-04T01:08:29.442958+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JDHXKAY","created_at":"2026-06-04T01:08:29.442958+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/2JDHXKAYJWQLMV6FJSH2M5ZAKT","json":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT.json","graph_json":"https://pith.science/api/pith-number/2JDHXKAYJWQLMV6FJSH2M5ZAKT/graph.json","events_json":"https://pith.science/api/pith-number/2JDHXKAYJWQLMV6FJSH2M5ZAKT/events.json","paper":"https://pith.science/paper/2JDHXKAY"},"agent_actions":{"view_html":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT","download_json":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT.json","view_paper":"https://pith.science/paper/2JDHXKAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01250&json=true","fetch_graph":"https://pith.science/api/pith-number/2JDHXKAYJWQLMV6FJSH2M5ZAKT/graph.json","fetch_events":"https://pith.science/api/pith-number/2JDHXKAYJWQLMV6FJSH2M5ZAKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT/action/storage_attestation","attest_author":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT/action/author_attestation","sign_citation":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT/action/citation_signature","submit_replication":"https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT/action/replication_record"}},"created_at":"2026-06-04T01:08:29.442958+00:00","updated_at":"2026-06-04T01:08:29.442958+00:00"}