.png){kind=icon}
返回
Distributed Stochastic Zeroth-Order Optimization With Compressed Communication
.png){kind=icon}
PRE
AI
DOI：10.1109/TAC.2025.3610109.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The dual challenges of high communication costs and gradient inaccessibility—common in privacy-sensitive systems or black-box environments—drive our work on communication-constrained, gradient-free distributed optimization. We propose a compressed distributed stochastic zeroth-order algorithm (Com-DSZO), which requires only two function evaluations per iteration and incorporates general compression operators. Rigorous analysis establishes a sublinear convergence rate for both smooth and nonsmooth objectives, explicitly characterizing the tradeoff between compression and convergence. Furthermore, we develop a variance-reduced variant (VR-Com-DSZO) under stochastic minibatch feedback. The effectiveness of the proposed algorithms is demonstrated through numerical experiments.
Keyword:
Compressed communication
multiagent systems
stochastic distributed optimization
zeroth-order optimization
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
.png){kind=icon}
Distributed Projection Subgradient Algorithm Over Time-Varying General Unbalanced Directed Graphs时变一般不平衡有向图上的分布式投影次梯度算法
PREAI
分享收藏
Randomized Gradient-Free Distributed Online Optimization via a Dynamic Regret Analysis基于动态后悔分析的随机无梯度分布式在线优化
OAAI
OAAI分享收藏Distributed Variable Sample-Size Stochastic Optimization With Fixed Step-Sizes具有固定步长的分布式可变样本大小随机优化OAAI
OAAI分享收藏
查看更多内容