Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent

DOI10.1137/16M1085905zbMath1353.65053OpenAlexW2547193634MaRDI QIDQ2832112

Peter Richtárik, Olivier Fercoq

Publication date: 7 November 2016

Published in: SIAM Review (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/16m1085905

zbMATH Keywords

complexitylinear programmingconvex optimizationsemidefinite programminggradient methodsaccelerationparallel methodsbig datapartial separabilityproximal methodsrandomized coordinate descentrandomized proximal gradient methodsseparable overapproximation

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Semidefinite programming (90C22) Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Linear programming (90C05) Parallel numerical computation (65Y05)

Related Items (9)

Stochastic subspace correction in Hilbert space ⋮ A block symmetric Gauss-Seidel decomposition theorem for convex composite quadratic programming and its applications ⋮ Large-Scale Nonconvex Optimization: Randomization, Gap Estimation, and Numerical Resolution ⋮ A Randomized Coordinate Descent Method with Volume Sampling ⋮ Variational analysis perspective on linear convergence of some first order methods for nonsmooth convex optimization problems ⋮ Stochastic subspace correction methods and fault tolerance ⋮ Block-proximal methods with spatially adapted acceleration ⋮ Computing the Best Approximation over the Intersection of a Polyhedral Set and the Doubly Nonnegative Cone ⋮ Linear convergence of prox-SVRG method for separable non-smooth convex optimization problems under bounded metric subregularity

Uses Software

• GrabCut
• KDD Cup

Cites Work

• Unnamed Item
• Unnamed Item
• Smooth minimization of non-smooth functions
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Parallel coordinate descent methods for big data optimization
• Inexact coordinate descent: complexity and preconditioning
• On optimal probabilities in stochastic coordinate descent methods
• On the complexity analysis of randomized block-coordinate descent methods
• Smooth minimization of nonsmooth functions with parallel coordinate descent methods
• Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
• Coordinate descent algorithms for lasso penalized regression
• Lectures on Modern Convex Optimization
• An Efficient Inexact ABCD Method for Least Squares Semidefinite Programming
• Distributed Coordinate Descent Method for Learning with Big Data
• Coordinate descent with arbitrary sampling I: algorithms and complexity^†
• Coordinate descent with arbitrary sampling II: expected separable overapproximation
• Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
• Nearly-Linear Time Positive LP Solver with Faster Convergence Rate
• Randomized Methods for Linear Constraints: Convergence Rates and Conditioning
• Semidefinite optimization
• Accelerated, Parallel, and Proximal Coordinate Descent
• An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
• Distributed Block Coordinate Descent for Minimizing Partially Separable Functions
• Parallel Random Coordinate Descent Method for Composite Minimization: Convergence Analysis and Error Bounds
• Monotone Operators and the Proximal Point Algorithm
• Augmented Lagrangians and Applications of the Proximal Point Algorithm in Convex Programming
• Coordinate Descent Face-Off: Primal or Dual?
• Semidefinite Programming
• Safe Feature Elimination in Sparse Supervised Learning
• Learning with Submodular Functions: A Convex Optimization Perspective
• Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
• Understanding Machine Learning
• An Asynchronous Parallel Stochastic Coordinate Descent Algorithm
• Handbook of semidefinite programming. Theory, algorithms, and applications
• Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization

This page was built for publication: Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent