arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.04207math.OCcs.DCcs.MAcs.SIstat.ML
收藏

随机最优化的群体算法

Swarming for Faster Convergence in Stochastic Optimization

Shi Pu, Alfredo Garcia

摘要:

我们研究了随机最优化的分布式框架,该框架受到自然界中发现的集体运动模型的启发(例如,具有温和的通信要求。具体而言,我们分析了一个方案,其中每一个$N > 1$独立的线程,实现在一个分布式和非同步的方式,随机梯度-下降算法,这是由一个群集电位扰动。假设同步引起的开销是不可忽略的,我们展示了基于群集的方法在(实时)收敛速度方面表现出比集中式算法(基于$N$观测的平均值)更好的性能。我们还得到了一个误差界,是单调递减的网络大小和连接。我们描述了该方案对于凸和非凸目标函数的有限时间性能。

英文摘要:

We study a distributed framework for stochastic optimization which is inspired by models of collective motion found in nature (e.g., swarming) with mild communication requirements. Specifically, we analyze a scheme in which each one of $N > 1$ independent threads, implements in a distributed and unsynchronized fashion, a stochastic gradient-descent algorithm which is perturbed by a swarming potential. Assuming the overhead caused by synchronization is not negligible, we show the swarming-based approach exhibits better performance than a centralized algorithm (based upon the average of $N$ observations) in terms of (real-time) convergence speed. We also derive an error bound that is monotone decreasing in network size and connectivity. We characterize the scheme's finite-time performances for both convex and non-convex objective functions.

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。

↑