{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:EE6DTBFP7DD4LCEW3JGM4MUOLO","short_pith_number":"pith:EE6DTBFP","schema_version":"1.0","canonical_sha256":"213c3984aff8c7c58896da4cce328e5bab2249faa651f509f3a2f5d462dc28d0","source":{"kind":"arxiv","id":"1507.00407","version":5},"attestation_state":"computed","paper":{"title":"Fast Convergence of Regularized Learning in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"Alekh Agarwal, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis","submitted_at":"2015-07-02T01:55:40Z","abstract_excerpt":"We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games. When each player in a game uses an algorithm from our class, their individual regret decays at $O(T^{-3/4})$, while the sum of utilities converges to an approximate optimum at $O(T^{-1})$--an improvement upon the worst case $O(T^{-1/2})$ rates. We show a black-box reduction for any algorithm in the class to achieve $\\tilde{O}(T^{-1/2})$ rates against an adversary, while mainta"},"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":"1507.00407","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2015-07-02T01:55:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"68cd5cae3c1be999fed5cb40b59c4c3688252f1a43f65ed925325b49858759e5","abstract_canon_sha256":"7e3f8b547af20b2ee16eb0ff2c85c1401973cca2026649388aff4889fcf0d132"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:32.946387Z","signature_b64":"++LGpVCqnTKavAHn9EuDzEQqpBT08A085niGy6Brd9Mhjo+9JAVCGwtWHIlCJpW61nl4ZSjhB28JNHG9Jl1NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213c3984aff8c7c58896da4cce328e5bab2249faa651f509f3a2f5d462dc28d0","last_reissued_at":"2026-05-18T01:24:32.945915Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:32.945915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Convergence of Regularized Learning in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"Alekh Agarwal, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis","submitted_at":"2015-07-02T01:55:40Z","abstract_excerpt":"We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games. When each player in a game uses an algorithm from our class, their individual regret decays at $O(T^{-3/4})$, while the sum of utilities converges to an approximate optimum at $O(T^{-1})$--an improvement upon the worst case $O(T^{-1/2})$ rates. We show a black-box reduction for any algorithm in the class to achieve $\\tilde{O}(T^{-1/2})$ rates against an adversary, while mainta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00407","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":""},"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":"1507.00407","created_at":"2026-05-18T01:24:32.945983+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.00407v5","created_at":"2026-05-18T01:24:32.945983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00407","created_at":"2026-05-18T01:24:32.945983+00:00"},{"alias_kind":"pith_short_12","alias_value":"EE6DTBFP7DD4","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"EE6DTBFP7DD4LCEW","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"EE6DTBFP","created_at":"2026-05-18T12:29:19.899920+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/EE6DTBFP7DD4LCEW3JGM4MUOLO","json":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO.json","graph_json":"https://pith.science/api/pith-number/EE6DTBFP7DD4LCEW3JGM4MUOLO/graph.json","events_json":"https://pith.science/api/pith-number/EE6DTBFP7DD4LCEW3JGM4MUOLO/events.json","paper":"https://pith.science/paper/EE6DTBFP"},"agent_actions":{"view_html":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO","download_json":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO.json","view_paper":"https://pith.science/paper/EE6DTBFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.00407&json=true","fetch_graph":"https://pith.science/api/pith-number/EE6DTBFP7DD4LCEW3JGM4MUOLO/graph.json","fetch_events":"https://pith.science/api/pith-number/EE6DTBFP7DD4LCEW3JGM4MUOLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO/action/storage_attestation","attest_author":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO/action/author_attestation","sign_citation":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO/action/citation_signature","submit_replication":"https://pith.science/pith/EE6DTBFP7DD4LCEW3JGM4MUOLO/action/replication_record"}},"created_at":"2026-05-18T01:24:32.945983+00:00","updated_at":"2026-05-18T01:24:32.945983+00:00"}