{"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"}