Linearized ADMM for Non-convex Non-smooth Optimization with Convergence Analysis
arXiv:1705.02502
Abstract
Linearized alternating direction method of multipliers (ADMM) as an extension of ADMM has been widely used to solve linearly constrained problems in signal processing, machine leaning, communications, and many other fields. Despite its broad applications in nonconvex optimization, for a great number of nonconvex and nonsmooth objective functions, its theoretical convergence guarantee is still an open problem. In this paper, we propose a two-block linearized ADMM and a multi-block parallel linearized ADMM for problems with nonconvex and nonsmooth objectives. Mathematically, we present that the algorithms can converge for a broader class of objective functions under less strict assumptions compared with previous works. Furthermore, our proposed algorithm can update coupled variables in parallel and work for less restrictive nonconvex problems, where the traditional ADMM may have difficulties in solving subproblems.
arXiv comment29 pages, 2 tables, 2 figures
References in corpus (7)
- Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation
- On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
- Multi-Agent Distributed Optimization via Inexact Consensus ADMM
- Parallel and Distributed Methods for Nonconvex Optimization--Part II: Applications
- Sparse Inverse Covariance Selection via Alternating Linearization Methods
- Parallel and Distributed Methods for Nonconvex Optimization-Part I: Theory
- Structured Nonconvex and Nonsmooth Optimization: Algorithms and Iteration Complexity Analysis
Cited by in corpus (7)
- Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks
- A Stochastic Alternating Direction Method of Multipliers for Non-smooth and Non-convex Optimization
- Fast and Provable ADMM for Learning with Generative Priors
- On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
- Iteration-complexity of a Jacobi-type non-Euclidean ADMM for multi-block linearly constrained nonconvex programs
- Accelerated Symmetric ADMM and Its Applications in Signal Processing
- A Novel Euler's Elastica based Segmentation Approach for Noisy Images via using the Progressive Hedging Algorithm