In this paper, we propose a randomized primal–dual proximal block coordinate updating framework for a general multi-block convex optimization model with coupled objective function and linear constraints. Assuming mere convexity, we establish its O(1 / t) convergence rate in terms of the objective value and feasibility measure. The framework includes several existing algorithms as special cases such as a primal–dual method for bilinear saddle-point problems (PD-S), the proximal Jacobian alternating direction method of multipliers (Prox-JADMM) and a randomized variant of the ADMM for multi-block convex optimization. Our analysis recovers and/or strengthens the convergence properties of several existing algorithms. For example, for PD-S our result leads to the same order of convergence rate without the previously assumed boundedness condition on the constraint sets, and for Prox-JADMM the new result provides convergence rate in terms of the objective value and the feasibility violation. It is well known that the original ADMM may fail to converge when the number of blocks exceeds two. Our result shows that if an appropriate randomization procedure is invoked to select the updating blocks, then a sublinear rate of convergence in expectation can be guaranteed for multi-block ADMM, without assuming any strong convexity. The new approach is also extended to solve problems where only a stochastic approximation of the subgradient of the objective is available, and we establish an O(1/t) convergence rate of the extended approach for solving stochastic programming.
|Original language||English (US)|
|Number of pages||46|
|Journal||Journal of the Operations Research Society of China|
|State||Published - Jun 5 2019|
Bibliographical noteFunding Information:
This work is partly supported by the National Science Foundation (Nos. DMS-1719549 and CMMI-1462408).
© 2018, Operations Research Society of China, Periodicals Agency of Shanghai University, Science Press, and Springer-Verlag GmbH Germany, part of Springer Nature.
- Alternating direction method of multipliers (ADMM)
- First-order stochastic approximation
- Iteration complexity
- Primal–dual method
- Randomized algorithm