{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RO3SLMZHD2ZLPERAIOGDGKFUFW","short_pith_number":"pith:RO3SLMZH","schema_version":"1.0","canonical_sha256":"8bb725b3271eb2b79220438c3328b42db42e3fbfa54c92ac46f3c009f1984a16","source":{"kind":"arxiv","id":"2206.00920","version":2},"attestation_state":"computed","paper":{"title":"Federated Learning with a Sampling Algorithm under Isoperimetry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adil Salim, Lukang Sun, Peter Richt\\'arik","submitted_at":"2022-06-02T08:19:03Z","abstract_excerpt":"Federated learning uses a set of techniques to efficiently distribute the training of a machine learning algorithm across several devices, who own the training data. These techniques critically rely on reducing the communication cost -- the main bottleneck -- between the devices and a central server. Federated learning algorithms usually take an optimization approach: they are algorithms for minimizing the training loss subject to communication (and other) constraints. In this work, we instead take a Bayesian approach for the training task, and propose a communication-efficient variant of the "},"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":"2206.00920","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T08:19:03Z","cross_cats_sorted":[],"title_canon_sha256":"a2e4698174330ad4ebea1d093b2cff4e9d11d2f4ed94ee77bff305cdc93f6de3","abstract_canon_sha256":"8a55bd86b3e821ed5feaef421db11dace8b137dc6daa6424fdd81264255cc1e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:35.205104Z","signature_b64":"I8I7W9khmxUTuQcPhKPzotRu+4D2QnHdsfihUzsodWZfAhlaxt7o6xJ0Gtir8FwH98TCj//3iI8QhursRt/BCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bb725b3271eb2b79220438c3328b42db42e3fbfa54c92ac46f3c009f1984a16","last_reissued_at":"2026-07-05T04:29:35.204580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:35.204580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with a Sampling Algorithm under Isoperimetry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adil Salim, Lukang Sun, Peter Richt\\'arik","submitted_at":"2022-06-02T08:19:03Z","abstract_excerpt":"Federated learning uses a set of techniques to efficiently distribute the training of a machine learning algorithm across several devices, who own the training data. These techniques critically rely on reducing the communication cost -- the main bottleneck -- between the devices and a central server. Federated learning algorithms usually take an optimization approach: they are algorithms for minimizing the training loss subject to communication (and other) constraints. In this work, we instead take a Bayesian approach for the training task, and propose a communication-efficient variant of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00920","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/2206.00920/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":"2206.00920","created_at":"2026-07-05T04:29:35.204640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00920v2","created_at":"2026-07-05T04:29:35.204640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00920","created_at":"2026-07-05T04:29:35.204640+00:00"},{"alias_kind":"pith_short_12","alias_value":"RO3SLMZHD2ZL","created_at":"2026-07-05T04:29:35.204640+00:00"},{"alias_kind":"pith_short_16","alias_value":"RO3SLMZHD2ZLPERA","created_at":"2026-07-05T04:29:35.204640+00:00"},{"alias_kind":"pith_short_8","alias_value":"RO3SLMZH","created_at":"2026-07-05T04:29:35.204640+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/RO3SLMZHD2ZLPERAIOGDGKFUFW","json":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW.json","graph_json":"https://pith.science/api/pith-number/RO3SLMZHD2ZLPERAIOGDGKFUFW/graph.json","events_json":"https://pith.science/api/pith-number/RO3SLMZHD2ZLPERAIOGDGKFUFW/events.json","paper":"https://pith.science/paper/RO3SLMZH"},"agent_actions":{"view_html":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW","download_json":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW.json","view_paper":"https://pith.science/paper/RO3SLMZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00920&json=true","fetch_graph":"https://pith.science/api/pith-number/RO3SLMZHD2ZLPERAIOGDGKFUFW/graph.json","fetch_events":"https://pith.science/api/pith-number/RO3SLMZHD2ZLPERAIOGDGKFUFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW/action/storage_attestation","attest_author":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW/action/author_attestation","sign_citation":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW/action/citation_signature","submit_replication":"https://pith.science/pith/RO3SLMZHD2ZLPERAIOGDGKFUFW/action/replication_record"}},"created_at":"2026-07-05T04:29:35.204640+00:00","updated_at":"2026-07-05T04:29:35.204640+00:00"}