摘要
This article is concerned with the multiagent optimization problem. A distributed randomized gradient-free mirror descent (DRGFMD) method is developed by introducing a randomized gradient-free oracle in the mirror descent scheme where the non-Euclidean Bregman divergence is used. The classical gradient descent method is generalized without using subgradient information of objective functions. The proposed algorithms are the first distributed non-Euclidean zeroth-order methods, which achieve an approximate O(1/root T) T-rate of convergence, recovering the best known optimal rate of distributed nonsmooth constrained convex optimization. Moreover, a decentralized reciprocal weighted averaging (RWA) approximating sequence is first investigated, the convergence for RWA sequence is shown to hold over time-varying graph. Rates of convergence are comprehensively explored for the algorithm with RWA (DRGFMD-RWA). The technique on constructing the decentralized RWA sequence provides new insight in searching for minimizers in distributed algorithms.
学科与关键词
- Distributed Stochastic Constrained Composite Optimization Over Time-Varying Network With a Class of Communication NoiseYu, Zhan*; Ho, Daniel W. C.; Yuan, Deming; Liu, JieIEEE Transactions on Cybernetics, 2023, 53(6): 3561-3573.被引 8
- Event-Triggered Distributed Stochastic Mirror Descent for Convex OptimizationXiong, Menghui; Zhang, Baoyong*; Ho, Daniel W. C.; Yuan, Deming; Xu, ShengyuanIEEE Transactions on Neural Networks and Learning Systems, 2023, 34(9): 6480-6491.被引 7
- Distributed Constrained Optimization With Delayed Subgradient Information Over Time-Varying Network Under Adaptive QuantizationLiu, Jie*; Yu, Zhan; Ho, Daniel W. C.IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(1): 143-156.被引 3
