Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210291264> ?p ?o ?g. }
- W4210291264 endingPage "2666" @default.
- W4210291264 startingPage "2641" @default.
- W4210291264 abstract "This paper deals with constrained convex problems, where the objective function is smooth and strongly convex, and the feasible set is described by a large number of closed convex (possibly nonpolyhedral) sets. In order to deal efficiently with the complicated constraints, we consider a dual formulation of this problem. We prove that the corresponding dual function satisfies a quadratic growth property on any sublevel set, provided that the primal objective function is smooth and strongly convex and the feasible set verifies Slater’s condition. We propose (accelerated) random coordinate descent algorithms that use the special composite structure of the dual problem. However, with the existing theory, one can prove only that such methods converge sublinearly. Based on our new quadratic growth property derived for the dual problem, we show that such methods have faster convergence, that is, the dual (accelerated) random coordinate descent algorithms converge linearly. Besides providing a general dual framework for the analysis of random dual coordinate descent schemes, our results resolve an open problem in the literature related to the convergence of the Dykstra algorithm on the best feasibility problem for a collection of convex sets. That is, we establish linear convergence rate for the random Dykstra algorithm when the convex sets just satisfy Slater’s condition and derive also a new accelerated variant for the Dykstra algorithm." @default.
- W4210291264 created "2022-02-08" @default.
- W4210291264 creator A5019114471 @default.
- W4210291264 creator A5064454585 @default.
- W4210291264 date "2022-11-01" @default.
- W4210291264 modified "2023-10-05" @default.
- W4210291264 title "Linear Convergence of Random Dual Coordinate Descent on Nonpolyhedral Convex Problems" @default.
- W4210291264 cites W1536329667 @default.
- W4210291264 cites W1946620893 @default.
- W4210291264 cites W1947202642 @default.
- W4210291264 cites W1964744380 @default.
- W4210291264 cites W1965073581 @default.
- W4210291264 cites W1975552883 @default.
- W4210291264 cites W1980200213 @default.
- W4210291264 cites W2003085133 @default.
- W4210291264 cites W2012180727 @default.
- W4210291264 cites W2021897193 @default.
- W4210291264 cites W2033121805 @default.
- W4210291264 cites W2033511209 @default.
- W4210291264 cites W2047043241 @default.
- W4210291264 cites W2073749939 @default.
- W4210291264 cites W2075660001 @default.
- W4210291264 cites W2081633016 @default.
- W4210291264 cites W2095984592 @default.
- W4210291264 cites W2113503719 @default.
- W4210291264 cites W2117686388 @default.
- W4210291264 cites W2124541940 @default.
- W4210291264 cites W2131247345 @default.
- W4210291264 cites W2152191514 @default.
- W4210291264 cites W2153374208 @default.
- W4210291264 cites W2162461247 @default.
- W4210291264 cites W2334285086 @default.
- W4210291264 cites W2592062427 @default.
- W4210291264 cites W2962943830 @default.
- W4210291264 cites W2963830980 @default.
- W4210291264 cites W2985739199 @default.
- W4210291264 cites W3100049367 @default.
- W4210291264 cites W4249667877 @default.
- W4210291264 doi "https://doi.org/10.1287/moor.2021.1222" @default.
- W4210291264 hasPublicationYear "2022" @default.
- W4210291264 type Work @default.
- W4210291264 citedByCount "0" @default.
- W4210291264 crossrefType "journal-article" @default.
- W4210291264 hasAuthorship W4210291264A5019114471 @default.
- W4210291264 hasAuthorship W4210291264A5064454585 @default.
- W4210291264 hasConcept C112680207 @default.
- W4210291264 hasConcept C12108790 @default.
- W4210291264 hasConcept C124952713 @default.
- W4210291264 hasConcept C126255220 @default.
- W4210291264 hasConcept C127162648 @default.
- W4210291264 hasConcept C14036430 @default.
- W4210291264 hasConcept C142362112 @default.
- W4210291264 hasConcept C145446738 @default.
- W4210291264 hasConcept C157553263 @default.
- W4210291264 hasConcept C157972887 @default.
- W4210291264 hasConcept C162324750 @default.
- W4210291264 hasConcept C177067428 @default.
- W4210291264 hasConcept C2524010 @default.
- W4210291264 hasConcept C2777303404 @default.
- W4210291264 hasConcept C2780980858 @default.
- W4210291264 hasConcept C28826006 @default.
- W4210291264 hasConcept C31258907 @default.
- W4210291264 hasConcept C33923547 @default.
- W4210291264 hasConcept C41008148 @default.
- W4210291264 hasConcept C49870271 @default.
- W4210291264 hasConcept C50522688 @default.
- W4210291264 hasConcept C57869625 @default.
- W4210291264 hasConcept C78458016 @default.
- W4210291264 hasConcept C86803240 @default.
- W4210291264 hasConceptScore W4210291264C112680207 @default.
- W4210291264 hasConceptScore W4210291264C12108790 @default.
- W4210291264 hasConceptScore W4210291264C124952713 @default.
- W4210291264 hasConceptScore W4210291264C126255220 @default.
- W4210291264 hasConceptScore W4210291264C127162648 @default.
- W4210291264 hasConceptScore W4210291264C14036430 @default.
- W4210291264 hasConceptScore W4210291264C142362112 @default.
- W4210291264 hasConceptScore W4210291264C145446738 @default.
- W4210291264 hasConceptScore W4210291264C157553263 @default.
- W4210291264 hasConceptScore W4210291264C157972887 @default.
- W4210291264 hasConceptScore W4210291264C162324750 @default.
- W4210291264 hasConceptScore W4210291264C177067428 @default.
- W4210291264 hasConceptScore W4210291264C2524010 @default.
- W4210291264 hasConceptScore W4210291264C2777303404 @default.
- W4210291264 hasConceptScore W4210291264C2780980858 @default.
- W4210291264 hasConceptScore W4210291264C28826006 @default.
- W4210291264 hasConceptScore W4210291264C31258907 @default.
- W4210291264 hasConceptScore W4210291264C33923547 @default.
- W4210291264 hasConceptScore W4210291264C41008148 @default.
- W4210291264 hasConceptScore W4210291264C49870271 @default.
- W4210291264 hasConceptScore W4210291264C50522688 @default.
- W4210291264 hasConceptScore W4210291264C57869625 @default.
- W4210291264 hasConceptScore W4210291264C78458016 @default.
- W4210291264 hasConceptScore W4210291264C86803240 @default.
- W4210291264 hasIssue "4" @default.
- W4210291264 hasLocation W42102912641 @default.
- W4210291264 hasLocation W42102912642 @default.
- W4210291264 hasOpenAccess W4210291264 @default.
- W4210291264 hasPrimaryLocation W42102912641 @default.