On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization
From MaRDI portal
Publication:4558510
zbMath1404.68112arXiv1607.02793MaRDI QIDQ4558510
Xing Guo Li, Han Liu, Tuo Zhao, Raman Arora, Mingyi Hong
Publication date: 22 November 2018
Full work available at URL: https://arxiv.org/abs/1607.02793
gradient descent; quadratic minimization; cyclic block coordinate descent; improved iteration complexity; strongly convex minimization
Related Items
Analyzing random permutations for cyclic coordinate descent, Two Symmetrized Coordinate Descent Methods Can Be $O(n^2)$ Times Slower Than the Randomized Version, Cyclic Coordinate Dual Averaging with Extrapolation, Block Policy Mirror Descent, Robust supervised learning with coordinate gradient descent, Local linear convergence of proximal coordinate descent algorithm, Pathwise coordinate optimization for sparse learning: algorithm and theory, Inexact variable metric stochastic block-coordinate descent for regularized optimization, New analysis of linear convergence of gradient-type methods via unifying error bound conditions
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- On the complexity analysis of randomized block-coordinate descent methods
- On the linear convergence of the alternating direction method of multipliers
- Iteration complexity analysis of block coordinate descent methods
- A coordinate gradient descent method for nonsmooth separable minimization
- Triangular truncation and finding the norm of a Hadamard multiplier
- A dual algorithm for the solution of nonlinear variational problems via finite element approximation
- Introductory lectures on convex optimization. A basic course.
- Pathwise coordinate optimization for sparse learning: algorithm and theory
- On non-ergodic convergence rate of Douglas-Rachford alternating direction method of multipliers
- Dual coordinate ascent methods for non-strictly convex minimization
- Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
- Pathwise coordinate optimization
- A Unified Convergence Analysis of Block Successive Minimization Methods for Nonsmooth Optimization
- On the Iteration Complexity of Cyclic Coordinate Gradient Descent Methods
- NESTA: A Fast and Accurate First-Order Method for Sparse Recovery
- SparseNet: Coordinate Descent With Nonconvex Penalties
- Matrix Analysis
- On the Linear Convergence of Descent Methods for Convex Essentially Smooth Minimization
- On the Nonasymptotic Convergence of Cyclic Coordinate Descent Methods
- Regularization and Variable Selection Via the Elastic Net
- Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems
- The huge Package for High-dimensional Undirected Graph Estimation in R
- On the Convergence of Block Coordinate Descent Type Methods
- Strong Rules for Discarding Predictors in Lasso-Type Problems
- Convergence of a block coordinate descent method for nondifferentiable minimization
- Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
