{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IYWINK4ZAUFRQX4N2RI4ZDX73G","short_pith_number":"pith:IYWINK4Z","schema_version":"1.0","canonical_sha256":"462c86ab99050b185f8dd451cc8effd986dc8ce42bd40886fb0d6677e7c8d56d","source":{"kind":"arxiv","id":"1904.05115","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dmitry Kovalev, Konstantin Mishchenko, Peter Richt\\'arik, Samuel Horv\\'ath, Sebastian Stich","submitted_at":"2019-04-10T11:34:43Z","abstract_excerpt":"We consider distributed optimization where the objective function is spread among different devices, each sending incremental model updates to a central server. To alleviate the communication bottleneck, recent work proposed various schemes to compress (e.g.\\ quantize or sparsify) the gradients, thereby introducing additional variance $\\omega \\geq 1$ that might slow down convergence. For strongly convex functions with condition number $\\kappa$ distributed among $n$ machines, we (i) give a scheme that converges in $\\mathcal{O}((\\kappa + \\kappa \\frac{\\omega}{n} + \\omega)$ $\\log (1/\\epsilon))$ st"},"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":"1904.05115","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-04-10T11:34:43Z","cross_cats_sorted":[],"title_canon_sha256":"c1c4d2a38e67d60aad9b0b7a19087befdd1f3a99b4969018f10cc1d271fe486f","abstract_canon_sha256":"e5b82133515b434931a8e125502c42f7e38f19bd7ef88500b8bdddb9368a604a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:54.098079Z","signature_b64":"jN1Go9fWON3VpejR15GTMVQ2cvTL3XrzJ0tCVANGr4Jh8yrV6LXKydIBZUDpbaf0pdKbcVBx0ck03Kq3Ph2yDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"462c86ab99050b185f8dd451cc8effd986dc8ce42bd40886fb0d6677e7c8d56d","last_reissued_at":"2026-05-17T23:48:54.097594Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:54.097594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dmitry Kovalev, Konstantin Mishchenko, Peter Richt\\'arik, Samuel Horv\\'ath, Sebastian Stich","submitted_at":"2019-04-10T11:34:43Z","abstract_excerpt":"We consider distributed optimization where the objective function is spread among different devices, each sending incremental model updates to a central server. To alleviate the communication bottleneck, recent work proposed various schemes to compress (e.g.\\ quantize or sparsify) the gradients, thereby introducing additional variance $\\omega \\geq 1$ that might slow down convergence. For strongly convex functions with condition number $\\kappa$ distributed among $n$ machines, we (i) give a scheme that converges in $\\mathcal{O}((\\kappa + \\kappa \\frac{\\omega}{n} + \\omega)$ $\\log (1/\\epsilon))$ st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05115","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":"1904.05115","created_at":"2026-05-17T23:48:54.097672+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05115v1","created_at":"2026-05-17T23:48:54.097672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05115","created_at":"2026-05-17T23:48:54.097672+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYWINK4ZAUFR","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYWINK4ZAUFRQX4N","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYWINK4Z","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24012","citing_title":"FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G","json":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G.json","graph_json":"https://pith.science/api/pith-number/IYWINK4ZAUFRQX4N2RI4ZDX73G/graph.json","events_json":"https://pith.science/api/pith-number/IYWINK4ZAUFRQX4N2RI4ZDX73G/events.json","paper":"https://pith.science/paper/IYWINK4Z"},"agent_actions":{"view_html":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G","download_json":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G.json","view_paper":"https://pith.science/paper/IYWINK4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05115&json=true","fetch_graph":"https://pith.science/api/pith-number/IYWINK4ZAUFRQX4N2RI4ZDX73G/graph.json","fetch_events":"https://pith.science/api/pith-number/IYWINK4ZAUFRQX4N2RI4ZDX73G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G/action/storage_attestation","attest_author":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G/action/author_attestation","sign_citation":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G/action/citation_signature","submit_replication":"https://pith.science/pith/IYWINK4ZAUFRQX4N2RI4ZDX73G/action/replication_record"}},"created_at":"2026-05-17T23:48:54.097672+00:00","updated_at":"2026-05-17T23:48:54.097672+00:00"}