{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DKIJPXFJSTY6EHVNZ6FDQXFUBZ","short_pith_number":"pith:DKIJPXFJ","schema_version":"1.0","canonical_sha256":"1a9097dca994f1e21eadcf8a385cb40e610c0ea026c3f7ab47244f08630bcf4b","source":{"kind":"arxiv","id":"2502.10020","version":5},"attestation_state":"computed","paper":{"title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Joongkyu Lee, Min-hwan Oh","submitted_at":"2025-02-14T09:01:12Z","abstract_excerpt":"In this paper, we propose an improved online confidence bound for multinomial logistic (MNL) models and apply this result to MNL bandits, achieving variance-dependent optimal regret. Recently, Lee & Oh (2024) established an online confidence bound for MNL models and achieved nearly minimax-optimal regret in MNL bandits. However, their results still depend on the norm-boundedness of the unknown parameter $B$ and the maximum size of possible outcomes $K$. To address this, we first derive an online confidence bound of $O\\left(\\sqrt{d \\log t} + B \\sqrt{d} \\right)$, which is a significant improveme"},"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":"2502.10020","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-14T09:01:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd59f1f129f6f1ba89144a7ed0e89f5ba2f50d539ee0c14d46006b1d710151fa","abstract_canon_sha256":"d77ad510f07c7efd72002f44b68f5b9a93bff9ddc3bd6b2eda0d4c31403d03c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:17.742635Z","signature_b64":"zW9IGgfGZmN1iAEM3iyfx+y10LiI2WRnLHt4aDUSSqEbVVhETOlISyVd+wqvvVn8Ggslol+F96GtC1kT4fwJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a9097dca994f1e21eadcf8a385cb40e610c0ea026c3f7ab47244f08630bcf4b","last_reissued_at":"2026-07-05T11:22:17.742062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:17.742062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Joongkyu Lee, Min-hwan Oh","submitted_at":"2025-02-14T09:01:12Z","abstract_excerpt":"In this paper, we propose an improved online confidence bound for multinomial logistic (MNL) models and apply this result to MNL bandits, achieving variance-dependent optimal regret. Recently, Lee & Oh (2024) established an online confidence bound for MNL models and achieved nearly minimax-optimal regret in MNL bandits. However, their results still depend on the norm-boundedness of the unknown parameter $B$ and the maximum size of possible outcomes $K$. To address this, we first derive an online confidence bound of $O\\left(\\sqrt{d \\log t} + B \\sqrt{d} \\right)$, which is a significant improveme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10020","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/2502.10020/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":"2502.10020","created_at":"2026-07-05T11:22:17.742135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10020v5","created_at":"2026-07-05T11:22:17.742135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10020","created_at":"2026-07-05T11:22:17.742135+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKIJPXFJSTY6","created_at":"2026-07-05T11:22:17.742135+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKIJPXFJSTY6EHVN","created_at":"2026-07-05T11:22:17.742135+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKIJPXFJ","created_at":"2026-07-05T11:22:17.742135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18800","citing_title":"Optimal Exploration of New Products under Assortment Decisions","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19768","citing_title":"Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19008","citing_title":"Optimal Online and Offline Algorithms for Contextual MNL with Applications to Assortment and Pricing","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18800","citing_title":"Optimal Exploration of New Products under Assortment Decisions","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ","json":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ.json","graph_json":"https://pith.science/api/pith-number/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/graph.json","events_json":"https://pith.science/api/pith-number/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/events.json","paper":"https://pith.science/paper/DKIJPXFJ"},"agent_actions":{"view_html":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ","download_json":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ.json","view_paper":"https://pith.science/paper/DKIJPXFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10020&json=true","fetch_graph":"https://pith.science/api/pith-number/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/action/storage_attestation","attest_author":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/action/author_attestation","sign_citation":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/action/citation_signature","submit_replication":"https://pith.science/pith/DKIJPXFJSTY6EHVNZ6FDQXFUBZ/action/replication_record"}},"created_at":"2026-07-05T11:22:17.742135+00:00","updated_at":"2026-07-05T11:22:17.742135+00:00"}