{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F2JAACN762NOLBESHJI6RF7GRP","short_pith_number":"pith:F2JAACN7","schema_version":"1.0","canonical_sha256":"2e920009bff69ae584923a51e897e68bcd2682e7362da6e3605df89706ad1f73","source":{"kind":"arxiv","id":"1905.12960","version":1},"attestation_state":"computed","paper":{"title":"On the Convergence of Memory-Based Distributed SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hao Gao, Shen-Yi Zhao, Wu-Jun Li","submitted_at":"2019-05-30T11:01:16Z","abstract_excerpt":"Distributed stochastic gradient descent~(DSGD) has been widely used for optimizing large-scale machine learning models, including both convex and non-convex models. With the rapid growth of model size, huge communication cost has been the bottleneck of traditional DSGD. Recently, many communication compression methods have been proposed. Memory-based distributed stochastic gradient descent~(M-DSGD) is one of the efficient methods since each worker communicates a sparse vector in each iteration so that the communication cost is small. Recent works propose the convergence rate of M-DSGD when it "},"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":"1905.12960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-30T11:01:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec99511e15422863ef1fd840ed0646dbbdaaf032c2e980df7e2f2fa1b27ef762","abstract_canon_sha256":"348db49957003e1f45511c9942c2bfb0f529147218705db136b4c2ee92bb724f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:39.255890Z","signature_b64":"dmeeoXXb+qqB3p81ucj/Dlwa7mXEOMMW77A+OtgQKiSlcSuUxIRelu17kyI5bURKeLR2PAnV9ZEg7I9h04UBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e920009bff69ae584923a51e897e68bcd2682e7362da6e3605df89706ad1f73","last_reissued_at":"2026-05-17T23:44:39.255468Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:39.255468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of Memory-Based Distributed SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hao Gao, Shen-Yi Zhao, Wu-Jun Li","submitted_at":"2019-05-30T11:01:16Z","abstract_excerpt":"Distributed stochastic gradient descent~(DSGD) has been widely used for optimizing large-scale machine learning models, including both convex and non-convex models. With the rapid growth of model size, huge communication cost has been the bottleneck of traditional DSGD. Recently, many communication compression methods have been proposed. Memory-based distributed stochastic gradient descent~(M-DSGD) is one of the efficient methods since each worker communicates a sparse vector in each iteration so that the communication cost is small. Recent works propose the convergence rate of M-DSGD when it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12960","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":""},"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":"1905.12960","created_at":"2026-05-17T23:44:39.255531+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12960v1","created_at":"2026-05-17T23:44:39.255531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12960","created_at":"2026-05-17T23:44:39.255531+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2JAACN762NO","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2JAACN762NOLBES","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2JAACN7","created_at":"2026-05-18T12:33:15.570797+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/F2JAACN762NOLBESHJI6RF7GRP","json":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP.json","graph_json":"https://pith.science/api/pith-number/F2JAACN762NOLBESHJI6RF7GRP/graph.json","events_json":"https://pith.science/api/pith-number/F2JAACN762NOLBESHJI6RF7GRP/events.json","paper":"https://pith.science/paper/F2JAACN7"},"agent_actions":{"view_html":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP","download_json":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP.json","view_paper":"https://pith.science/paper/F2JAACN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12960&json=true","fetch_graph":"https://pith.science/api/pith-number/F2JAACN762NOLBESHJI6RF7GRP/graph.json","fetch_events":"https://pith.science/api/pith-number/F2JAACN762NOLBESHJI6RF7GRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP/action/storage_attestation","attest_author":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP/action/author_attestation","sign_citation":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP/action/citation_signature","submit_replication":"https://pith.science/pith/F2JAACN762NOLBESHJI6RF7GRP/action/replication_record"}},"created_at":"2026-05-17T23:44:39.255531+00:00","updated_at":"2026-05-17T23:44:39.255531+00:00"}