{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NAA2CZQ7UL5SQ7BOF5WNOPDFUS","short_pith_number":"pith:NAA2CZQ7","schema_version":"1.0","canonical_sha256":"6801a1661fa2fb287c2e2f6cd73c65a4ba6564e6d02f65229f9327f475b7178c","source":{"kind":"arxiv","id":"2205.04180","version":4},"attestation_state":"computed","paper":{"title":"EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Kai Yi, Laurent Condat, Peter Richt\\'arik","submitted_at":"2022-05-09T10:44:23Z","abstract_excerpt":"In distributed or federated optimization and learning, communication between the different computing units is often the bottleneck and gradient compression is widely used to reduce the number of bits sent within each communication round of iterative methods. There are two classes of compression operators and separate algorithms making use of them. In the case of unbiased random compressors with bounded variance (e.g., rand-k), the DIANA algorithm of Mishchenko et al. (2019), which implements a variance reduction technique for handling the variance introduced by compression, is the current stat"},"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":"2205.04180","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-09T10:44:23Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"e4733f41a89bb734e6efce37a444d76072a35cf72f163ecad65d80ee116c41be","abstract_canon_sha256":"bead560c5538ac571608b9bba7b0b33efc8504f6e027143326b39a07ae84d673"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:58.646260Z","signature_b64":"25MM5rBWdr/6H0XQK/e/hHPtWkwMrp1CJPFwub85dkc14RL0fpdmlTHHT6lHFhlwZF9dzIcOKR1OtT4GY5gnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6801a1661fa2fb287c2e2f6cd73c65a4ba6564e6d02f65229f9327f475b7178c","last_reissued_at":"2026-07-05T05:47:58.645698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:58.645698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Kai Yi, Laurent Condat, Peter Richt\\'arik","submitted_at":"2022-05-09T10:44:23Z","abstract_excerpt":"In distributed or federated optimization and learning, communication between the different computing units is often the bottleneck and gradient compression is widely used to reduce the number of bits sent within each communication round of iterative methods. There are two classes of compression operators and separate algorithms making use of them. In the case of unbiased random compressors with bounded variance (e.g., rand-k), the DIANA algorithm of Mishchenko et al. (2019), which implements a variance reduction technique for handling the variance introduced by compression, is the current stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04180","kind":"arxiv","version":4},"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/2205.04180/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":"2205.04180","created_at":"2026-07-05T05:47:58.645761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04180v4","created_at":"2026-07-05T05:47:58.645761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04180","created_at":"2026-07-05T05:47:58.645761+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAA2CZQ7UL5S","created_at":"2026-07-05T05:47:58.645761+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAA2CZQ7UL5SQ7BO","created_at":"2026-07-05T05:47:58.645761+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAA2CZQ7","created_at":"2026-07-05T05:47:58.645761+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":178,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18174","citing_title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":280,"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":175,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07795","citing_title":"Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS","json":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS.json","graph_json":"https://pith.science/api/pith-number/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/graph.json","events_json":"https://pith.science/api/pith-number/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/events.json","paper":"https://pith.science/paper/NAA2CZQ7"},"agent_actions":{"view_html":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS","download_json":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS.json","view_paper":"https://pith.science/paper/NAA2CZQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04180&json=true","fetch_graph":"https://pith.science/api/pith-number/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/graph.json","fetch_events":"https://pith.science/api/pith-number/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/action/storage_attestation","attest_author":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/action/author_attestation","sign_citation":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/action/citation_signature","submit_replication":"https://pith.science/pith/NAA2CZQ7UL5SQ7BOF5WNOPDFUS/action/replication_record"}},"created_at":"2026-07-05T05:47:58.645761+00:00","updated_at":"2026-07-05T05:47:58.645761+00:00"}