1. Dual Averaging Push for Distributed Convex Optimization Over Time-Varying Directed Graph.
- Author
-
Liang, Shu, Wang, Le Yi, and Yin, George
- Subjects
- *
ALGORITHMS , *SUBGRADIENT methods , *DISTRIBUTED algorithms , *DIRECTED graphs , *NONSMOOTH optimization , *MULTIAGENT systems , *CONVEX functions - Abstract
Inspired by the subgradient push method developed recently by Nedić et al. we present a distributed dual averaging push algorithm for constrained nonsmooth convex optimization over time-varying directed graph. Our algorithm combines the dual averaging method with the push-sum technique and achieves an $O(1/ \sqrt{k})$ convergence rate. Compared with the subgradient push algorithm, our algorithm, first, addresses the constrained problems, and, second, has a faster convergence rate, and, third, simplifies the convergence analysis. We also generalize the proposed algorithm so that input variables of subgradient oracles have guaranteed convergence. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF