{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XCZFGROGETXECZDYTDS36WL45S","short_pith_number":"pith:XCZFGROG","schema_version":"1.0","canonical_sha256":"b8b25345c624ee41647898e5bf597cec9ca3739b120baf11fc6293e28df542d6","source":{"kind":"arxiv","id":"2010.00091","version":1},"attestation_state":"computed","paper":{"title":"Error Compensated Distributed SGD Can Be Accelerated","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Peter Richt\\'arik, Tong Zhang, Xun Qian","submitted_at":"2020-09-30T20:09:31Z","abstract_excerpt":"Gradient compression is a recent and increasingly popular technique for reducing the communication cost in distributed training of large-scale machine learning models. In this work we focus on developing efficient distributed methods that can work for any compressor satisfying a certain contraction property, which includes both unbiased (after appropriate scaling) and biased compressors such as RandK and TopK. Applied naively, gradient compression introduces errors that either slow down convergence or lead to divergence. A popular technique designed to tackle this issue is error compensation/e"},"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":"2010.00091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-09-30T20:09:31Z","cross_cats_sorted":[],"title_canon_sha256":"259f6c9ba6035dd7d9461bcc27ba740cd17b63fba0e5914654514c3f7b53f429","abstract_canon_sha256":"2a434d0a5b65606667111a1651071bf7815ff1c0aa63ac115d9a802d051bb26a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:30.280924Z","signature_b64":"kSL6ua/3wEHRPBISFqxjiMQW6blgcJwZLHPo0s5/DEuGOGdqgapfPF8a4COTDbaaUi1YdtV5Pd6bZnfyUuR1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8b25345c624ee41647898e5bf597cec9ca3739b120baf11fc6293e28df542d6","last_reissued_at":"2026-07-05T01:39:30.280439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:30.280439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error Compensated Distributed SGD Can Be Accelerated","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Peter Richt\\'arik, Tong Zhang, Xun Qian","submitted_at":"2020-09-30T20:09:31Z","abstract_excerpt":"Gradient compression is a recent and increasingly popular technique for reducing the communication cost in distributed training of large-scale machine learning models. In this work we focus on developing efficient distributed methods that can work for any compressor satisfying a certain contraction property, which includes both unbiased (after appropriate scaling) and biased compressors such as RandK and TopK. Applied naively, gradient compression introduces errors that either slow down convergence or lead to divergence. A popular technique designed to tackle this issue is error compensation/e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00091","kind":"arxiv","version":1},"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/2010.00091/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":"2010.00091","created_at":"2026-07-05T01:39:30.280498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.00091v1","created_at":"2026-07-05T01:39:30.280498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00091","created_at":"2026-07-05T01:39:30.280498+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCZFGROGETXE","created_at":"2026-07-05T01:39:30.280498+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCZFGROGETXECZDY","created_at":"2026-07-05T01:39:30.280498+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCZFGROG","created_at":"2026-07-05T01:39:30.280498+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/XCZFGROGETXECZDYTDS36WL45S","json":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S.json","graph_json":"https://pith.science/api/pith-number/XCZFGROGETXECZDYTDS36WL45S/graph.json","events_json":"https://pith.science/api/pith-number/XCZFGROGETXECZDYTDS36WL45S/events.json","paper":"https://pith.science/paper/XCZFGROG"},"agent_actions":{"view_html":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S","download_json":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S.json","view_paper":"https://pith.science/paper/XCZFGROG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.00091&json=true","fetch_graph":"https://pith.science/api/pith-number/XCZFGROGETXECZDYTDS36WL45S/graph.json","fetch_events":"https://pith.science/api/pith-number/XCZFGROGETXECZDYTDS36WL45S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S/action/storage_attestation","attest_author":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S/action/author_attestation","sign_citation":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S/action/citation_signature","submit_replication":"https://pith.science/pith/XCZFGROGETXECZDYTDS36WL45S/action/replication_record"}},"created_at":"2026-07-05T01:39:30.280498+00:00","updated_at":"2026-07-05T01:39:30.280498+00:00"}