{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EAJKWKHBUGZHGLL3PGOPV2RMJJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1005abee3bf93f4778efe8a8507ec01ce617d2ea2ba8061d11a858247612d0fa","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-30T03:03:03Z","title_canon_sha256":"ff173f55cd8eb35f0c598d188c500288f7e9c6d54ee09c027537ac7d65690afa"},"schema_version":"1.0","source":{"id":"2408.16981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16981","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16981v2","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16981","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"EAJKWKHBUGZH","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"EAJKWKHBUGZHGLL3","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"EAJKWKHB","created_at":"2026-07-05T09:28:13Z"}],"graph_snapshots":[{"event_id":"sha256:721cd442f4b0ad7e6aaaefbeed9310705a5137dd2519d25c5318eea57aaffb27","target":"graph","created_at":"2026-07-05T09:28:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.16981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of federated Q-learning, where $M$ agents aim to collaboratively learn the optimal Q-function of an unknown infinite-horizon Markov decision process with finite state and action spaces. We investigate the trade-off between sample and communication complexities for the widely used class of intermittent communication algorithms. We first establish the converse result, where it is shown that a federated Q-learning algorithm that offers any speedup with respect to the number of agents in the per-agent sample complexity needs to incur a communication cost of at least an orde","authors_text":"Sudeep Salgia, Yuejie Chi","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-30T03:03:03Z","title":"The Sample-Communication Complexity Trade-off in Federated Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16981","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b0bc75fda4f6e886a3c9c0c85a78866a66d298398fd6a1f350a1c30cf2edef0","target":"record","created_at":"2026-07-05T09:28:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1005abee3bf93f4778efe8a8507ec01ce617d2ea2ba8061d11a858247612d0fa","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-30T03:03:03Z","title_canon_sha256":"ff173f55cd8eb35f0c598d188c500288f7e9c6d54ee09c027537ac7d65690afa"},"schema_version":"1.0","source":{"id":"2408.16981","kind":"arxiv","version":2}},"canonical_sha256":"2012ab28e1a1b2732d7b799cfaea2c4a7667140993a1142ad03b330c0fab9504","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2012ab28e1a1b2732d7b799cfaea2c4a7667140993a1142ad03b330c0fab9504","first_computed_at":"2026-07-05T09:28:13.508725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:13.508725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wwW5jMz06odCxvqB7t/7XADKEMjhzBHgdKKhOIllK2gTpzfBSkrWAE4bXkeir3Kz0UBZ6TqfW51NZFT9YAgwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:13.509212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b0bc75fda4f6e886a3c9c0c85a78866a66d298398fd6a1f350a1c30cf2edef0","sha256:721cd442f4b0ad7e6aaaefbeed9310705a5137dd2519d25c5318eea57aaffb27"],"state_sha256":"cad301cabedf8d840562ad521c31b3ff525a99719a52be007cc9b8b5a3b28bec"}