arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.04532math.OC
收藏

具有聚集结构的分布式随机组合最优化问题的数值方法

Numerical Methods for Distributed Stochastic Compositional Optimization Problems with Aggregative Structure

Shengchao Zhao, Yongchao Liu

摘要:

研究了网络上的分布式随机组合最优化问题,其中所有智能体的内层函数是每个智能体的私有期望函数之和。针对内层函数的聚集结构,采用混合方差约简方法获取各Agent的私有期望函数信息,并采用动态一致性机制跟踪各Agent的内层函数信息.然后结合标准的分布式随机梯度下降法,提出了一种分布式聚集随机合成梯度下降法。当目标函数光滑时,该方法具有最优的收敛速度$\mathcal{O}\left(K^{-1/2}\right)$ .我们进一步将该方法与通信压缩相结合,提出了通信压缩变量分布聚集随机合成梯度下降法。所提出的方法的压缩变体保持最佳的收敛速度$\mathcal{O}\left(K^{-1/2}\right)$。分散强化学习的仿真实验验证了所提方法的有效性。

英文摘要:

The paper studies the distributed stochastic compositional optimization problems over networks, where all the agents' inner-level function is the sum of each agent's private expectation function. Focusing on the aggregative structure of the inner-level function, we employ the hybrid variance reduction method to obtain the information on each agent's private expectation function, and apply the dynamic consensus mechanism to track the information on each agent's inner-level function. Then by combining with the standard distributed stochastic gradient descent method, we propose a distributed aggregative stochastic compositional gradient descent method. When the objective function is smooth, the proposed method achieves the optimal convergence rate $\mathcal{O}\left(K^{-1/2}\right)$. We further combine the proposed method with the communication compression and propose the communication compressed variant distributed aggregative stochastic compositional gradient descent method. The compressed variant of the proposed method maintains the optimal convergence rate $\mathcal{O}\left(K^{-1/2}\right)$. Simulated experiments on decentralized reinforcement learning verify the effectiveness of the proposed methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑