Convergence Analysis and Design of Multi-block ADMM via Switched Control Theory
arXiv:1709.05528
Abstract
We consider three challenges in multi-block Alternating Direction Method of Multipliers (ADMM): building convergence conditions for ADMM with any block (variable) sequence, finding available block sequences to be fit for ADMM, and designing useful parameter controllers for ADMM with unfixed parameters. To address these challenges, we develop a switched control framework for studying multi-block ADMM. First, since ADMM recursively and alternately updates the block-variables, it is converted into a discrete-time switched dynamical system. Second, we study exponential stability and stabilizability of the switched system for linear convergence analysis and design of ADMM by employing switched Lyapunov functions. Moreover, linear matrix inequalities conditions are proposed to ensure convergence of ADMM under arbitrary sequence, to find convergent sequences, and to design the fixed parameters. These conditions are checked and solved by employing semidefinite programming. Numerical experiments further verify the effectiveness of our proposed theories.
arXiv comment19 pages, 4 figures
References in corpus (5)
- Asynchronous Distributed ADMM for Large-Scale Optimization- Part I: Algorithm and Convergence Analysis
- OptNet: Differentiable Optimization as a Layer in Neural Networks
- A Unified Algorithmic Framework for Block-Structured Optimization Involving Big Data
- Dissipativity Theory for Nesterov's Accelerated Method
- Fast Proximal Linearized Alternating Direction Method of Multiplier with Parallel Splitting