{"paper":{"title":"Error Feedback Shines when Features are Rare","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Elnur Gasanov, Konstantin Burlachenko, Peter Richt\\'arik","submitted_at":"2023-05-24T15:52:07Z","abstract_excerpt":"We provide the first proof that gradient descent $\\left({\\color{green}\\sf GD}\\right)$ with greedy sparsification $\\left({\\color{green}\\sf TopK}\\right)$ and error feedback $\\left({\\color{green}\\sf EF}\\right)$ can obtain better communication complexity than vanilla ${\\color{green}\\sf GD}$ when solving the distributed optimization problem $\\min_{x\\in \\mathbb{R}^d} {f(x)=\\frac{1}{n}\\sum_{i=1}^n f_i(x)}$, where $n$ = # of clients, $d$ = # of features, and $f_1,\\dots,f_n$ are smooth nonconvex functions. Despite intensive research since 2014 when ${\\color{green}\\sf EF}$ was first proposed by Seide et"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15264","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/2305.15264/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"}