Distributed Stochastic Zeroth-Order Optimization With Compressed Communication

• 成果类型: Article
• 署名作者: Hua, Youqing; Liu, Shuai; Hong, Yiguang; Ren, Wei
• 署名单位: Shandong University; Tongji University; Tongji University; University of California System; University of California Riverside
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2025.3610109
• 发表日期: 2026
• 关键词: convergence; algorithms

摘要

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.