{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YSGGSMF2MISCROEVPAXM4GDK76","short_pith_number":"pith:YSGGSMF2","schema_version":"1.0","canonical_sha256":"c48c6930ba622428b895782ece186affaab68096cdc2fb4056d3cdc621346807","source":{"kind":"arxiv","id":"2109.05700","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Heterogeneity in Robust Federated Best-Arm Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, George Pappas, Hamed Hassani","submitted_at":"2021-09-13T04:22:21Z","abstract_excerpt":"We study a federated variant of the best-arm identification problem in stochastic multi-armed bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via a server to identify the best arm (i.e., the arm with the highest mean reward) with prescribed confidence. For this problem, we propose Fed-SEL, a simple communication-efficient algorithm that builds on successive elimination techniques and involves local sampling steps at the clients. To study the performance of Fed-SEL, we introduce a notion of arm-heterogeneity that captures the level of dissimilarity betw"},"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":"2109.05700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-13T04:22:21Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"5ed9aac1bf272f93b937a03cf788bed4d17ae6c45d42092e7bdde2f60dbd7d37","abstract_canon_sha256":"8f558ab8db81fa9efc4e63ceba4f855f8e24e244888e306a468ac60d1286a1f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:46.593188Z","signature_b64":"K9EwlXEZJpw581A0+rsi3G5FdMfZk12BSBtz4MfCbPKUWKaCM3wdngGKPgyZoR/gN5S7eyVWeHd2I8CIdDq+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c48c6930ba622428b895782ece186affaab68096cdc2fb4056d3cdc621346807","last_reissued_at":"2026-07-05T03:14:46.592798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:46.592798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Heterogeneity in Robust Federated Best-Arm Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, George Pappas, Hamed Hassani","submitted_at":"2021-09-13T04:22:21Z","abstract_excerpt":"We study a federated variant of the best-arm identification problem in stochastic multi-armed bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via a server to identify the best arm (i.e., the arm with the highest mean reward) with prescribed confidence. For this problem, we propose Fed-SEL, a simple communication-efficient algorithm that builds on successive elimination techniques and involves local sampling steps at the clients. To study the performance of Fed-SEL, we introduce a notion of arm-heterogeneity that captures the level of dissimilarity betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05700","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.05700/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":"2109.05700","created_at":"2026-07-05T03:14:46.592854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05700v2","created_at":"2026-07-05T03:14:46.592854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05700","created_at":"2026-07-05T03:14:46.592854+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSGGSMF2MISC","created_at":"2026-07-05T03:14:46.592854+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSGGSMF2MISCROEV","created_at":"2026-07-05T03:14:46.592854+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSGGSMF2","created_at":"2026-07-05T03:14:46.592854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.22480","citing_title":"Service Placement in Small Cell Networks Using Distributed Best Arm Identification in Linear Bandits","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76","json":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76.json","graph_json":"https://pith.science/api/pith-number/YSGGSMF2MISCROEVPAXM4GDK76/graph.json","events_json":"https://pith.science/api/pith-number/YSGGSMF2MISCROEVPAXM4GDK76/events.json","paper":"https://pith.science/paper/YSGGSMF2"},"agent_actions":{"view_html":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76","download_json":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76.json","view_paper":"https://pith.science/paper/YSGGSMF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05700&json=true","fetch_graph":"https://pith.science/api/pith-number/YSGGSMF2MISCROEVPAXM4GDK76/graph.json","fetch_events":"https://pith.science/api/pith-number/YSGGSMF2MISCROEVPAXM4GDK76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76/action/storage_attestation","attest_author":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76/action/author_attestation","sign_citation":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76/action/citation_signature","submit_replication":"https://pith.science/pith/YSGGSMF2MISCROEVPAXM4GDK76/action/replication_record"}},"created_at":"2026-07-05T03:14:46.592854+00:00","updated_at":"2026-07-05T03:14:46.592854+00:00"}