Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950998989> ?p ?o ?g. }
- W2950998989 endingPage "3340" @default.
- W2950998989 startingPage "3325" @default.
- W2950998989 abstract "This paper proposes and analyzes a communication-efficient distributed optimization framework for general nonconvex nonsmooth signal processing and machine learning problems under an asynchronous protocol. At each iteration, worker machines compute gradients of a known empirical loss function using their own local data, and a master machine solves a related minimization problem to update the current estimate. We prove that for nonconvex nonsmooth problems, the proposed algorithm converges to a stationary point with a sublinear rate over the number of communication rounds, coinciding with the best theoretical rate that can be achieved for this class of problems. Linear convergence to a global minimum is established without any statistical assumptions on the local data for problems characterized by composite loss functions whose smooth part is strongly convex. Extensive numerical experiments verify that the performance of the proposed approach indeed improves - sometimes significantly - over other state-of-the-art algorithms in terms of total communication efficiency." @default.
- W2950998989 created "2019-06-27" @default.
- W2950998989 creator A5001325170 @default.
- W2950998989 creator A5011305900 @default.
- W2950998989 date "2020-01-01" @default.
- W2950998989 modified "2023-09-25" @default.
- W2950998989 title "A Provably Communication-Efficient Asynchronous Distributed Inference Method for Convex and Nonconvex Problems" @default.
- W2950998989 cites W1568130442 @default.
- W2950998989 cites W1627780903 @default.
- W2950998989 cites W1974661392 @default.
- W2950998989 cites W1975900269 @default.
- W2950998989 cites W2039050532 @default.
- W2950998989 cites W2044207982 @default.
- W2950998989 cites W2044212084 @default.
- W2950998989 cites W2049469158 @default.
- W2950998989 cites W2060393849 @default.
- W2950998989 cites W2074128440 @default.
- W2950998989 cites W2078831169 @default.
- W2950998989 cites W2079482358 @default.
- W2950998989 cites W2101876299 @default.
- W2950998989 cites W2117412539 @default.
- W2950998989 cites W2127881260 @default.
- W2950998989 cites W2154834860 @default.
- W2950998989 cites W2155723734 @default.
- W2950998989 cites W2266148951 @default.
- W2950998989 cites W2295566694 @default.
- W2950998989 cites W2295652899 @default.
- W2950998989 cites W2338807306 @default.
- W2950998989 cites W2526083046 @default.
- W2950998989 cites W2580937131 @default.
- W2950998989 cites W2605994693 @default.
- W2950998989 cites W2755388561 @default.
- W2950998989 cites W2892002891 @default.
- W2950998989 cites W2912544891 @default.
- W2950998989 cites W2918997734 @default.
- W2950998989 cites W2920766117 @default.
- W2950998989 cites W2962696932 @default.
- W2950998989 cites W2962760808 @default.
- W2950998989 cites W2962989062 @default.
- W2950998989 cites W2963090384 @default.
- W2950998989 cites W2963173886 @default.
- W2950998989 cites W2963321497 @default.
- W2950998989 cites W2963648037 @default.
- W2950998989 cites W2963649943 @default.
- W2950998989 cites W2963855576 @default.
- W2950998989 cites W2964231067 @default.
- W2950998989 cites W3100513551 @default.
- W2950998989 cites W4210458578 @default.
- W2950998989 cites W4292363360 @default.
- W2950998989 doi "https://doi.org/10.1109/tsp.2020.2996374" @default.
- W2950998989 hasPublicationYear "2020" @default.
- W2950998989 type Work @default.
- W2950998989 sameAs 2950998989 @default.
- W2950998989 citedByCount "0" @default.
- W2950998989 crossrefType "journal-article" @default.
- W2950998989 hasAuthorship W2950998989A5001325170 @default.
- W2950998989 hasAuthorship W2950998989A5011305900 @default.
- W2950998989 hasBestOaLocation W29509989892 @default.
- W2950998989 hasConcept C112680207 @default.
- W2950998989 hasConcept C11413529 @default.
- W2950998989 hasConcept C117160843 @default.
- W2950998989 hasConcept C126255220 @default.
- W2950998989 hasConcept C127162648 @default.
- W2950998989 hasConcept C134306372 @default.
- W2950998989 hasConcept C14036430 @default.
- W2950998989 hasConcept C145446738 @default.
- W2950998989 hasConcept C151319957 @default.
- W2950998989 hasConcept C157972887 @default.
- W2950998989 hasConcept C162324750 @default.
- W2950998989 hasConcept C189237950 @default.
- W2950998989 hasConcept C2524010 @default.
- W2950998989 hasConcept C2777303404 @default.
- W2950998989 hasConcept C31258907 @default.
- W2950998989 hasConcept C33923547 @default.
- W2950998989 hasConcept C41008148 @default.
- W2950998989 hasConcept C50522688 @default.
- W2950998989 hasConcept C57869625 @default.
- W2950998989 hasConcept C78458016 @default.
- W2950998989 hasConcept C86803240 @default.
- W2950998989 hasConceptScore W2950998989C112680207 @default.
- W2950998989 hasConceptScore W2950998989C11413529 @default.
- W2950998989 hasConceptScore W2950998989C117160843 @default.
- W2950998989 hasConceptScore W2950998989C126255220 @default.
- W2950998989 hasConceptScore W2950998989C127162648 @default.
- W2950998989 hasConceptScore W2950998989C134306372 @default.
- W2950998989 hasConceptScore W2950998989C14036430 @default.
- W2950998989 hasConceptScore W2950998989C145446738 @default.
- W2950998989 hasConceptScore W2950998989C151319957 @default.
- W2950998989 hasConceptScore W2950998989C157972887 @default.
- W2950998989 hasConceptScore W2950998989C162324750 @default.
- W2950998989 hasConceptScore W2950998989C189237950 @default.
- W2950998989 hasConceptScore W2950998989C2524010 @default.
- W2950998989 hasConceptScore W2950998989C2777303404 @default.
- W2950998989 hasConceptScore W2950998989C31258907 @default.
- W2950998989 hasConceptScore W2950998989C33923547 @default.
- W2950998989 hasConceptScore W2950998989C41008148 @default.
- W2950998989 hasConceptScore W2950998989C50522688 @default.
- W2950998989 hasConceptScore W2950998989C57869625 @default.