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 2108.05078math.OC
收藏

基于Fixed Step-sizes的分布变量样本随机最优化

Distributed Variable Sample-size Stochastic Optimization with Fixed Step-sizes

Jinlong Lei, Peng Yi, Jie Chen, Yiguang Hong

摘要:

本文研究了随机切换网络上的分布式随机最优化问题,在该问题中,多个智能体协作地最小化所有智能体的局部期望值凸费用函数的平均值.由于梯度观测的随机性、局部函数的分布性和通信拓扑的随机性,在固定步长下具有收敛保证的分布式算法尚未实现。这项工作将方差减少计划到分布式随机梯度跟踪算法,其中局部梯度估计通过在可变数量的采样梯度的平均。具有同分布和独立分布(i.i.d.)随机网络中,我们证明了在固定步长下,所有代理的迭代几乎必然收敛到相同的最优解。当全局费用函数是强凸的且样本量以几何速率增加时,我们证明了迭代几何收敛于唯一的最优解,并建立了迭代、预言和通信复杂度.算法的性能,包括速率和复杂度分析,进一步研究了恒定的步长和多项式增加的样本量。最后,通过数值例子说明了经验算法的性能。

英文摘要:

The paper considers distributed stochastic optimization over randomly switching networks, where agents collaboratively minimize the average of all agents' local expectation-valued convex cost functions. Due to the stochasticity in gradient observations, distributedness of local functions, and randomness of communication topologies, distributed algorithms with a convergence guarantee under fixed step-sizes have not been achieved yet. This work incorporates variance reduction scheme into the distributed stochastic gradient tracking algorithm, where local gradients are estimated by averaging across a variable number of sampled gradients. With an identically and independently distributed (i.i.d.) random network, we show that all agents' iterates converge almost surely to the same optimal solution under fixed step-sizes. When the global cost function is strongly convex and the sample size increases at a geometric rate, we prove that the iterates geometrically converge to the unique optimal solution, and establish the iteration, oracle, and communication complexity. The algorithm performance including rate and complexity analysis are further investigated with constant step-sizes and a polynomially increasing sample size. Finally, the empirical algorithm performance are illustrated with numerical examples.

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。

↑