{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BMR3W4KO75AR2RTZZCW2UCIMK3","short_pith_number":"pith:BMR3W4KO","schema_version":"1.0","canonical_sha256":"0b23bb714eff411d4679c8adaa090c56cc873bb57393df43aab24f7330873ec7","source":{"kind":"arxiv","id":"1904.12233","version":2},"attestation_state":"computed","paper":{"title":"Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark Sellke, S\\'ebastien Bubeck, Yuanzhi Li, Yuval Peres","submitted_at":"2019-04-28T00:21:04Z","abstract_excerpt":"We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem. The model assumes no communication at all between the players, and furthermore when two (or more) players select the same action this results in a maximal loss. We prove the first $\\sqrt{T}$-type regret guarantee for this problem, under the feedback model where collisions are announced to the colliding players. Such a bound was not known even for the simpler stochastic version. We also prove the first sublinear guarantee for the feedback model where collision information is not available, namel"},"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":"1904.12233","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-28T00:21:04Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"ed704af550f4c95bb86dfc135a271fcb74caa2eb291965b161f0c840393d7b7c","abstract_canon_sha256":"cb47e5712248f8dca439ac7eefa212d04b35747b3d0bdb50e4287d2ba2a6e0c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:11.900198Z","signature_b64":"hzWLUIdnM/iIKyTZqRRvkgIXjF6RB3N7S5poHqbdEtihJ1vsANHiDuc/agh0kM2Gk4yC9k5UX3Z4GgSzHoD0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b23bb714eff411d4679c8adaa090c56cc873bb57393df43aab24f7330873ec7","last_reissued_at":"2026-05-17T23:47:11.899818Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:11.899818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark Sellke, S\\'ebastien Bubeck, Yuanzhi Li, Yuval Peres","submitted_at":"2019-04-28T00:21:04Z","abstract_excerpt":"We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem. The model assumes no communication at all between the players, and furthermore when two (or more) players select the same action this results in a maximal loss. We prove the first $\\sqrt{T}$-type regret guarantee for this problem, under the feedback model where collisions are announced to the colliding players. Such a bound was not known even for the simpler stochastic version. We also prove the first sublinear guarantee for the feedback model where collision information is not available, namel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12233","kind":"arxiv","version":2},"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":"1904.12233","created_at":"2026-05-17T23:47:11.899879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12233v2","created_at":"2026-05-17T23:47:11.899879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12233","created_at":"2026-05-17T23:47:11.899879+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMR3W4KO75AR","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMR3W4KO75AR2RTZ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMR3W4KO","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2306.04498","citing_title":"Near-Optimal Privacy-Preserving Learning for Max-Min Fair Multi-Agent Bandits","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3","json":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3.json","graph_json":"https://pith.science/api/pith-number/BMR3W4KO75AR2RTZZCW2UCIMK3/graph.json","events_json":"https://pith.science/api/pith-number/BMR3W4KO75AR2RTZZCW2UCIMK3/events.json","paper":"https://pith.science/paper/BMR3W4KO"},"agent_actions":{"view_html":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3","download_json":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3.json","view_paper":"https://pith.science/paper/BMR3W4KO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12233&json=true","fetch_graph":"https://pith.science/api/pith-number/BMR3W4KO75AR2RTZZCW2UCIMK3/graph.json","fetch_events":"https://pith.science/api/pith-number/BMR3W4KO75AR2RTZZCW2UCIMK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3/action/storage_attestation","attest_author":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3/action/author_attestation","sign_citation":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3/action/citation_signature","submit_replication":"https://pith.science/pith/BMR3W4KO75AR2RTZZCW2UCIMK3/action/replication_record"}},"created_at":"2026-05-17T23:47:11.899879+00:00","updated_at":"2026-05-17T23:47:11.899879+00:00"}