{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNQWPOHYJBQKOQG2VOFF3QPG65","short_pith_number":"pith:FNQWPOHY","schema_version":"1.0","canonical_sha256":"2b6167b8f84860a740daab8a5dc1e6f7794b51fefcaed1f5065ad057fed72b3e","source":{"kind":"arxiv","id":"2408.08395","version":1},"attestation_state":"computed","paper":{"title":"Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Baoxiang Wang, Jing Dong, Yaoliang Yu","submitted_at":"2024-08-15T19:42:41Z","abstract_excerpt":"We study the problem of no-regret learning algorithms for general monotone and smooth games and their last-iterate convergence properties. Specifically, we investigate the problem under bandit feedback and strongly uncoupled dynamics, which allows modular development of the multi-player system that applies to a wide range of real applications. We propose a mirror-descent-based algorithm, which converges in $O(T^{-1/4})$ and is also no-regret. The result is achieved by a dedicated use of two regularizations and the analysis of the fixed point thereof. The convergence rate is further improved to"},"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":"2408.08395","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-08-15T19:42:41Z","cross_cats_sorted":[],"title_canon_sha256":"9714044e27b65e2864a11f1911e1a5064d2f66fe062d1f69194a36ae51dab57e","abstract_canon_sha256":"66851f913014b4fc3f784e2aeac00b818b8693d1bfbcb2d49fe6d48542aa01ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:53.847039Z","signature_b64":"gl9SVsgGpagS15IxP4a3/vmGiCsBzFK7W+P7g8/ZEn0yhhrKPoTdy3+KuTC1ULJmHO9S6gi/NP6V8CRRQ0bnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b6167b8f84860a740daab8a5dc1e6f7794b51fefcaed1f5065ad057fed72b3e","last_reissued_at":"2026-07-05T08:55:53.846663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:53.846663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Baoxiang Wang, Jing Dong, Yaoliang Yu","submitted_at":"2024-08-15T19:42:41Z","abstract_excerpt":"We study the problem of no-regret learning algorithms for general monotone and smooth games and their last-iterate convergence properties. Specifically, we investigate the problem under bandit feedback and strongly uncoupled dynamics, which allows modular development of the multi-player system that applies to a wide range of real applications. We propose a mirror-descent-based algorithm, which converges in $O(T^{-1/4})$ and is also no-regret. The result is achieved by a dedicated use of two regularizations and the analysis of the fixed point thereof. The convergence rate is further improved to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08395","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/2408.08395/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":"2408.08395","created_at":"2026-07-05T08:55:53.846717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08395v1","created_at":"2026-07-05T08:55:53.846717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08395","created_at":"2026-07-05T08:55:53.846717+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNQWPOHYJBQK","created_at":"2026-07-05T08:55:53.846717+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNQWPOHYJBQKOQG2","created_at":"2026-07-05T08:55:53.846717+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNQWPOHY","created_at":"2026-07-05T08:55:53.846717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09363","citing_title":"Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16087","citing_title":"The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65","json":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65.json","graph_json":"https://pith.science/api/pith-number/FNQWPOHYJBQKOQG2VOFF3QPG65/graph.json","events_json":"https://pith.science/api/pith-number/FNQWPOHYJBQKOQG2VOFF3QPG65/events.json","paper":"https://pith.science/paper/FNQWPOHY"},"agent_actions":{"view_html":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65","download_json":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65.json","view_paper":"https://pith.science/paper/FNQWPOHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08395&json=true","fetch_graph":"https://pith.science/api/pith-number/FNQWPOHYJBQKOQG2VOFF3QPG65/graph.json","fetch_events":"https://pith.science/api/pith-number/FNQWPOHYJBQKOQG2VOFF3QPG65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65/action/storage_attestation","attest_author":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65/action/author_attestation","sign_citation":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65/action/citation_signature","submit_replication":"https://pith.science/pith/FNQWPOHYJBQKOQG2VOFF3QPG65/action/replication_record"}},"created_at":"2026-07-05T08:55:53.846717+00:00","updated_at":"2026-07-05T08:55:53.846717+00:00"}