An Empirical Study of ADMM for Nonconvex Problems

Abstract

The alternating direction method of multipliers (ADMM) is a common optimization tool for solving constrained and non-differentiable problems. We provide an empirical study of the practical performance of ADMM on several nonconvex applications, including l0 regularized linear regression, l0 regularized image denoising, phase retrieval, and eigenvector computation. Our experiments suggest that ADMM performs well on a broad class of non-convex problems. Moreover, recently proposed adaptive ADMM methods, which automatically tune penalty parameters as the method runs, can improve algorithm efficiency and solution quality compared to ADMM with a non-tuned penalty.

NIPS nonconvex workshop

References in corpus (1)

• Convergence of Bregman alternating direction method with multipliers for nonconvex composite problems

Cited by in corpus (6)

• How is Distributed ADMM Affected by Network Topology?
• Data Multiplexing in Radio Interferometric Calibration
• Algorithms and software for projections onto intersections of convex and non-convex sets with applications to inverse problems
• Solving Constrained CASH Problems with ADMM
• Non-negative Factorization of the Occurrence Tensor from Financial Contracts
• Semi-Definite Relaxation Based ADMM for Cooperative Planning and Control of Connected Autonomous Vehicles