{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WNC3FKUMJNPZ4TZK3TVS4XZPNY","short_pith_number":"pith:WNC3FKUM","schema_version":"1.0","canonical_sha256":"b345b2aa8c4b5f9e4f2adceb2e5f2f6e0b034ea4c5ed85f861c2260cfa43f827","source":{"kind":"arxiv","id":"2112.13097","version":3},"attestation_state":"computed","paper":{"title":"Faster Rates for Compressed Federated Learning with Client-Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.DS","math.OC"],"primary_cat":"cs.LG","authors_text":"Haoyu Zhao, Konstantin Burlachenko, Peter Richt\\'arik, Zhize Li","submitted_at":"2021-12-24T16:28:18Z","abstract_excerpt":"Due to the communication bottleneck in distributed and federated learning applications, algorithms using communication compression have attracted significant attention and are widely used in practice. Moreover, the huge number, high heterogeneity and limited availability of clients result in high client-variance. This paper addresses these two issues together by proposing compressed and client-variance reduced methods COFIG and FRECON. We prove an $O(\\frac{(1+\\omega)^{3/2}\\sqrt{N}}{S\\epsilon^2}+\\frac{(1+\\omega)N^{2/3}}{S\\epsilon^2})$ bound on the number of communication rounds of COFIG in 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":"2112.13097","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-24T16:28:18Z","cross_cats_sorted":["cs.DC","cs.DS","math.OC"],"title_canon_sha256":"7519df688d38ce6ae8fb8c819d031508705bfb592089c205e1777f2e102f9bed","abstract_canon_sha256":"8d2e18ec91d2c22e48704c4bf6c3025e1d0448ad4fe4050029010eba7cf4b23d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:29.214819Z","signature_b64":"5X60Z7teuMHpoIHBzwm6fj3SC+uChBM6yTpLZnxrGtuIbvz8PyPh7vu5b9u5rh8L8usgvUzazhL7xZsTD4JXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b345b2aa8c4b5f9e4f2adceb2e5f2f6e0b034ea4c5ed85f861c2260cfa43f827","last_reissued_at":"2026-07-05T06:53:29.214270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:29.214270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster Rates for Compressed Federated Learning with Client-Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.DS","math.OC"],"primary_cat":"cs.LG","authors_text":"Haoyu Zhao, Konstantin Burlachenko, Peter Richt\\'arik, Zhize Li","submitted_at":"2021-12-24T16:28:18Z","abstract_excerpt":"Due to the communication bottleneck in distributed and federated learning applications, algorithms using communication compression have attracted significant attention and are widely used in practice. Moreover, the huge number, high heterogeneity and limited availability of clients result in high client-variance. This paper addresses these two issues together by proposing compressed and client-variance reduced methods COFIG and FRECON. We prove an $O(\\frac{(1+\\omega)^{3/2}\\sqrt{N}}{S\\epsilon^2}+\\frac{(1+\\omega)N^{2/3}}{S\\epsilon^2})$ bound on the number of communication rounds of COFIG in the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13097","kind":"arxiv","version":3},"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/2112.13097/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":"2112.13097","created_at":"2026-07-05T06:53:29.214338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.13097v3","created_at":"2026-07-05T06:53:29.214338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13097","created_at":"2026-07-05T06:53:29.214338+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNC3FKUMJNPZ","created_at":"2026-07-05T06:53:29.214338+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNC3FKUMJNPZ4TZK","created_at":"2026-07-05T06:53:29.214338+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNC3FKUM","created_at":"2026-07-05T06:53:29.214338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20866","citing_title":"LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18174","citing_title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":270,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08871","citing_title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07795","citing_title":"Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY","json":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY.json","graph_json":"https://pith.science/api/pith-number/WNC3FKUMJNPZ4TZK3TVS4XZPNY/graph.json","events_json":"https://pith.science/api/pith-number/WNC3FKUMJNPZ4TZK3TVS4XZPNY/events.json","paper":"https://pith.science/paper/WNC3FKUM"},"agent_actions":{"view_html":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY","download_json":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY.json","view_paper":"https://pith.science/paper/WNC3FKUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.13097&json=true","fetch_graph":"https://pith.science/api/pith-number/WNC3FKUMJNPZ4TZK3TVS4XZPNY/graph.json","fetch_events":"https://pith.science/api/pith-number/WNC3FKUMJNPZ4TZK3TVS4XZPNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY/action/storage_attestation","attest_author":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY/action/author_attestation","sign_citation":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY/action/citation_signature","submit_replication":"https://pith.science/pith/WNC3FKUMJNPZ4TZK3TVS4XZPNY/action/replication_record"}},"created_at":"2026-07-05T06:53:29.214338+00:00","updated_at":"2026-07-05T06:53:29.214338+00:00"}