Restarting the accelerated coordinate descent method with a rough strong convexity estimate
Authors:
- 10 October 2019
- journal article
- research article
- Published by Springer Nature in Computational Optimization and Applications
- Vol. 75 (1) , 63-91
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Engineering and Physical Sciences Research Council (EP/K02325X/1)
- Centre for Numerical Analysis and Intelligent Software
- Orange (Phi-TAB)
- Agence Nationale de la Recherche (ANR-11-LABX-0056-LMH)
This publication has 21 references indexed in Scilit:
- Error Bounds, Quadratic Growth, and Linear Convergence of Proximal MethodsMathematics of Operations Research, 2018
- Katyusha: the first direct acceleration of stochastic gradient methods2017
- From error bounds to the complexity of first-order descent methods for convex functionsMathematical Programming, 2016
- Linearly convergent away-step conditional gradient for non-strongly convex functionsMathematical Programming, 2016
- Stochastic intermediate gradient method for convex optimization problemsDoklady Mathematics, 2016
- An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk MinimizationSIAM Journal on Optimization, 2015
- Accelerated, Parallel, and Proximal Coordinate DescentSIAM Journal on Optimization, 2015
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal AlgorithmsSIAM Journal on Optimization, 2013
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- Pathwise coordinate optimizationThe Annals of Applied Statistics, 2007