An Empirical Study of ADMM for Nonconvex Problems
arXiv:1612.03349
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.
arXiv commentNIPS nonconvex workshop
References in corpus (17)
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Rejoinder to "Least angle regression" by Efron et al
- Least Angle Regression
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- An Alternating Direction Algorithm for Matrix Completion with Nonnegative Factors
- Global Convergence of ADMM in Nonconvex Nonsmooth Optimization
- Parallel Algorithms for Constrained Tensor Factorization via the Alternating Direction Method of Multipliers
- Convergence of Bregman alternating direction method with multipliers for nonconvex composite problems
- Adaptive ADMM with Spectral Penalty Parameter Selection
- Iterative Algorithms for Ptychographic Phase Retrieval
- MADMM: a generic algorithm for non-smooth optimization on manifolds
Cited by in corpus (8)
- How is Distributed ADMM Affected by Network Topology?
- Alternating Direction Method of Multipliers for Constrained Iterative LQR in Autonomous Driving
- 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
- Generalized Minkowski sets for the regularization of inverse problems
- Semi-Definite Relaxation Based ADMM for Cooperative Planning and Control of Connected Autonomous Vehicles
- Non-negative Factorization of the Occurrence Tensor from Financial Contracts