Coordinate descent with arbitrary sampling II: expected separable overapproximation

DOI10.1080/10556788.2016.1190361zbMath1365.90206arXiv1412.8063OpenAlexW2962990180WikidataQ56813560 ScholiaQ56813560MaRDI QIDQ2829566

Peter Richtárik, Zheng Qu

Publication date: 8 November 2016

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1412.8063

zbMATH Keywords

randomized methodscoordinate descentarbitrary samplingexpected separable overapproximationparallel and distributed coordinate descent

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Derivative-free methods and methods using generalized derivatives (90C56)

Related Items (15)

Parallel random block-coordinate forward-backward algorithm: a unified convergence analysis ⋮ On optimal probabilities in stochastic coordinate descent methods ⋮ Empirical risk minimization: probabilistic complexity and stepsize strategy ⋮ Unnamed Item ⋮ Local linear convergence of proximal coordinate descent algorithm ⋮ Faster convergence of a randomized coordinate descent method for linearly constrained optimization problems ⋮ On the complexity of parallel coordinate descent ⋮ Unnamed Item ⋮ Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods ⋮ A discrete dynamics approach to sparse calculation and applied in ontology science ⋮ Stochastic quasi-gradient methods: variance reduction via Jacobian sketching ⋮ Fastest rates for stochastic mirror descent methods ⋮ Restarting the accelerated coordinate descent method with a rough strong convexity estimate ⋮ Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent ⋮ Convergence Analysis of Inexact Randomized Iterative Methods

Cites Work

• Unnamed Item
• Parallel coordinate descent methods for big data optimization
• A random coordinate descent algorithm for optimization problems with composite objective function and linear coupled constraints
• Coordinate descent algorithms
• Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
• Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
• Separable approximations and decomposition methods for the augmented Lagrangian
• Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties
• Accelerated, Parallel, and Proximal Coordinate Descent
• An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
• On the Convergence of Block Coordinate Descent Type Methods
• Convergence of a block coordinate descent method for nondifferentiable minimization

This page was built for publication: Coordinate descent with arbitrary sampling II: expected separable overapproximation