arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09714math.OCcs.DCcs.MA
收藏

一种带动量的加速分布式随机梯度方法

An Accelerated Distributed Stochastic Gradient Method with Momentum

Kun Huang, Shi Pu, Angelia Nedić

AI总结:

本文提出带动量加速的分布式随机梯度方法DSMT,利用动量跟踪与无循环切比雪夫加速,在一般方差条件下达到与集中式SGD相当的收敛速率,且瞬态时间最短。

摘要:

在本文中,我们提出了一种带动量的加速分布式随机梯度方法,用于求解分布式优化问题,其中一组$n$个智能体在连通网络上协作最小化局部目标函数的平均值。该方法被称为“分布式随机动量跟踪(DSMT)”,是一种单循环算法,利用动量跟踪技术以及无循环切比雪夫加速(LCA)方法。我们证明,在关于随机梯度的一般方差条件下,DSMT能够渐近地达到与集中式随机梯度下降(SGD)方法相当的收敛速率。此外,对于最小化一般光滑目标函数,DSMT达到此类速率所需的迭代次数(瞬态时间)表现为$\mathcal{O}(n^{5/3}/(1-λ))$,而在Polyak-Łojasiewicz(PL)条件下为$\mathcal{O}(\sqrt{n/(1-λ)})$。这里,项$1-λ$表示与底层网络拓扑相关的混合矩阵的谱间隙。值得注意的是,所获得的结果不依赖于每次迭代中的多节点通信或随机梯度累积,并且据我们所知,在该设置下瞬态时间是最短的。

英文摘要:

In this paper, we introduce an accelerated distributed stochastic gradient method with momentum for solving the distributed optimization problem, where a group of $n$ agents collaboratively minimize the average of the local objective functions over a connected network. The method, termed ``Distributed Stochastic Momentum Tracking (DSMT)'', is a single-loop algorithm that utilizes the momentum tracking technique as well as the Loopless Chebyshev Acceleration (LCA) method. We show that DSMT can asymptotically achieve comparable convergence rates as centralized stochastic gradient descent (SGD) method under a general variance condition regarding the stochastic gradients. Moreover, the number of iterations (transient times) required for DSMT to achieve such rates behaves as $\mathcal{O}(n^{5/3}/(1-λ))$ for minimizing general smooth objective functions, and $\mathcal{O}(\sqrt{n/(1-λ)})$ under the Polyak-Łojasiewicz (PL) condition. Here, the term $1-λ$ denotes the spectral gap of the mixing matrix related to the underlying network topology. Notably, the obtained results do not rely on multiple inter-node communications or stochastic gradient accumulation per iteration, and the transient times are the shortest under the setting to the best of our knowledge.

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。

↑