{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WBTYSNBJOFKENEX4RSFSK7CWRC","short_pith_number":"pith:WBTYSNBJ","schema_version":"1.0","canonical_sha256":"b06789342971544692fc8c8b257c5688b63eb5ee6d39c24020a216895b540f32","source":{"kind":"arxiv","id":"2107.04518","version":1},"attestation_state":"computed","paper":{"title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baihe Huang, Jason D. Lee, Jiaqi Yang, Kaixuan Huang, Qi Lei, Runzhe Wang, Sham M. Kakade","submitted_at":"2021-07-09T16:04:24Z","abstract_excerpt":"Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large family of bandit problems where the unknown underlying reward function is non-concave, including the low-rank generalized linear bandit problems and two-layer neural network with polynomial activation bandit problem. For the low-rank generalized linear bandit problem, we provide a minimax-optimal algorithm in the dimension, refuting both conjectures in [LMT21, JWWN19]. Our algorithms are based on a unified zeroth-order o"},"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":"2107.04518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T16:04:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37f0227eb2ee03c8ce4af63abd1756a45fd0d4f8877c65f669331ebb85a6f2de","abstract_canon_sha256":"33dc99c3a5096b7fc124cb5ba27d88085f337a12be6d064ae3034a8f5aad5ba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:34.201793Z","signature_b64":"9wSYEah+f4ZN3L84RYQcCW59iXJMtXOLYjDm9t7HkXXCEjy/B0sedR/+i1XtdUiulXJH+IeYGieXjOnxN63EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b06789342971544692fc8c8b257c5688b63eb5ee6d39c24020a216895b540f32","last_reissued_at":"2026-07-05T02:56:34.201374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:34.201374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baihe Huang, Jason D. Lee, Jiaqi Yang, Kaixuan Huang, Qi Lei, Runzhe Wang, Sham M. Kakade","submitted_at":"2021-07-09T16:04:24Z","abstract_excerpt":"Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large family of bandit problems where the unknown underlying reward function is non-concave, including the low-rank generalized linear bandit problems and two-layer neural network with polynomial activation bandit problem. For the low-rank generalized linear bandit problem, we provide a minimax-optimal algorithm in the dimension, refuting both conjectures in [LMT21, JWWN19]. Our algorithms are based on a unified zeroth-order o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04518","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/2107.04518/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":"2107.04518","created_at":"2026-07-05T02:56:34.201434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04518v1","created_at":"2026-07-05T02:56:34.201434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04518","created_at":"2026-07-05T02:56:34.201434+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBTYSNBJOFKE","created_at":"2026-07-05T02:56:34.201434+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBTYSNBJOFKENEX4","created_at":"2026-07-05T02:56:34.201434+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBTYSNBJ","created_at":"2026-07-05T02:56:34.201434+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/WBTYSNBJOFKENEX4RSFSK7CWRC","json":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC.json","graph_json":"https://pith.science/api/pith-number/WBTYSNBJOFKENEX4RSFSK7CWRC/graph.json","events_json":"https://pith.science/api/pith-number/WBTYSNBJOFKENEX4RSFSK7CWRC/events.json","paper":"https://pith.science/paper/WBTYSNBJ"},"agent_actions":{"view_html":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC","download_json":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC.json","view_paper":"https://pith.science/paper/WBTYSNBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04518&json=true","fetch_graph":"https://pith.science/api/pith-number/WBTYSNBJOFKENEX4RSFSK7CWRC/graph.json","fetch_events":"https://pith.science/api/pith-number/WBTYSNBJOFKENEX4RSFSK7CWRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC/action/storage_attestation","attest_author":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC/action/author_attestation","sign_citation":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC/action/citation_signature","submit_replication":"https://pith.science/pith/WBTYSNBJOFKENEX4RSFSK7CWRC/action/replication_record"}},"created_at":"2026-07-05T02:56:34.201434+00:00","updated_at":"2026-07-05T02:56:34.201434+00:00"}