提出一种带误差反馈的模块化分布式非凸学习算法，有效抑制通信压缩误差。
Modular Distributed Nonconvex Learning with Error Feedback
- 融合ADMM与梯度法，兼顾鲁棒性与计算效率
- 引入随机积分项，确保几乎必然收敛到驻点
- 适用于非凸分类任务，适合大规模分布式学习场景
本文设计了一种基于随机压缩通信的新型分布式学习算法。采用模块化思路，结合ADMM的稳健性与梯度方法的高效性；同时引入随机积分动作（误差反馈），实现几乎必然地消除压缩误差。在非凸场景下，利用基于随机时标分离的系统理论工具，证明了算法几乎必然渐近收敛至问题的驻点集合。数值仿真验证了其在非凸分类任务中的有效性。
原文摘要 · Abstract (English)
In this paper, we design a novel distributed learning algorithm using stochastic compressed communications. In detail, we pursue a modular approach, merging ADMM and a gradient-based approach, benefiting from the robustness of the former and the computational efficiency of the latter. Additionally, we integrate a stochastic integral action (error feedback) enabling almost sure rejection of the compression error. We analyze the resulting method in nonconvex scenarios and guarantee almost sure asymptotic convergence to the set of stationary points of the problem. This result is obtained using system-theoretic tools based on stochastic timescale separation. We corroborate our findings with numerical simulations in nonconvex classification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。