Accelerated Block Coordinate Proximal Gradients with Applications in High Dimensional Statistics

Abstract

Nonconvex optimization problems arise in different research fields and arouse lots of attention in signal processing, statistics and machine learning. In this work, we explore the accelerated proximal gradient method and some of its variants which have been shown to converge under nonconvex context recently. We show that a novel variant proposed here, which exploits adaptive momentum and block coordinate update with specific update rules, further improves the performance of a broad class of nonconvex problems. In applications to sparse linear regression with regularizations like Lasso, grouped Lasso, capped ${\ell }_1$ and SCAP, the proposed scheme enjoys provable local linear convergence, with experimental justification.

arXiv comment10th NIPS Workshop on Optimization for Machine Learning (NIPS 2017). 8 pages, 4 figures

References in corpus (4)

• Nearly unbiased variable selection under minimax concave penalty
• A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems
• Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection
• Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization