{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6HEMEEVL545SVXNFKYZLCZZSPU","short_pith_number":"pith:6HEMEEVL","schema_version":"1.0","canonical_sha256":"f1c8c212abef3b2adda55632b167327d3a213a53dab2429898ff4a2bf0c5b87c","source":{"kind":"arxiv","id":"2102.04168","version":5},"attestation_state":"computed","paper":{"title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Yang, Kefan Dong, Tengyu Ma","submitted_at":"2021-02-08T12:41:56Z","abstract_excerpt":"This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statistically intractable even for one-layer neural net bandit with a deterministic reward. For both nonlinear bandit and RL, the paper presents a model-based algorithm, Virtual Ascent with Online Model Learner (ViOlin), which provably converges to a local maximum with sample complexity that only depends on the sequential Rademacher complexity of the model class. Our results imply nov"},"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":"2102.04168","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T12:41:56Z","cross_cats_sorted":[],"title_canon_sha256":"79d7394d48d869598eb896c4f8697a12818abb16cabb944b458fa895597c3055","abstract_canon_sha256":"41450de42d6f79d7a1761e3367f1a6c3f6f5ec8b2cf9f5a2e1e19677d61d0b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:36.304456Z","signature_b64":"dTBPW07jz2jPV4JCdX4LOv3LzIkJZXRTGyyvaw74gRBTNvq8V0TJthw6vaQYw1703wvwJH8CzLOIOS750kLqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1c8c212abef3b2adda55632b167327d3a213a53dab2429898ff4a2bf0c5b87c","last_reissued_at":"2026-07-05T04:45:36.304049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:36.304049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Yang, Kefan Dong, Tengyu Ma","submitted_at":"2021-02-08T12:41:56Z","abstract_excerpt":"This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statistically intractable even for one-layer neural net bandit with a deterministic reward. For both nonlinear bandit and RL, the paper presents a model-based algorithm, Virtual Ascent with Online Model Learner (ViOlin), which provably converges to a local maximum with sample complexity that only depends on the sequential Rademacher complexity of the model class. Our results imply nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04168","kind":"arxiv","version":5},"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/2102.04168/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":"2102.04168","created_at":"2026-07-05T04:45:36.304106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04168v5","created_at":"2026-07-05T04:45:36.304106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04168","created_at":"2026-07-05T04:45:36.304106+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HEMEEVL545S","created_at":"2026-07-05T04:45:36.304106+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HEMEEVL545SVXNF","created_at":"2026-07-05T04:45:36.304106+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HEMEEVL","created_at":"2026-07-05T04:45:36.304106+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/6HEMEEVL545SVXNFKYZLCZZSPU","json":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU.json","graph_json":"https://pith.science/api/pith-number/6HEMEEVL545SVXNFKYZLCZZSPU/graph.json","events_json":"https://pith.science/api/pith-number/6HEMEEVL545SVXNFKYZLCZZSPU/events.json","paper":"https://pith.science/paper/6HEMEEVL"},"agent_actions":{"view_html":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU","download_json":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU.json","view_paper":"https://pith.science/paper/6HEMEEVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04168&json=true","fetch_graph":"https://pith.science/api/pith-number/6HEMEEVL545SVXNFKYZLCZZSPU/graph.json","fetch_events":"https://pith.science/api/pith-number/6HEMEEVL545SVXNFKYZLCZZSPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU/action/storage_attestation","attest_author":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU/action/author_attestation","sign_citation":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU/action/citation_signature","submit_replication":"https://pith.science/pith/6HEMEEVL545SVXNFKYZLCZZSPU/action/replication_record"}},"created_at":"2026-07-05T04:45:36.304106+00:00","updated_at":"2026-07-05T04:45:36.304106+00:00"}