SLiSeS: Subsampled Line Search Spectral Gradient Method for Finite Sums

arXiv (Cornell University)(2023)

引用 0|浏览4
暂无评分
摘要
The spectral gradient method is known to be a powerful low-cost tool for solving large-scale optimization problems. In this paper, our goal is to exploit its advantages in the stochastic optimization framework, especially in the case of mini-batch subsampling that is often used in big data settings. To allow the spectral coefficient to properly explore the underlying approximate Hessian spectrum, we keep the same subsample for several iterations before subsampling again. We analyze the required algorithmic features and the conditions for almost sure convergence, and present initial numerical results that show the advantages of the proposed method.
更多
查看译文
关键词
finite sums,gradient,search,line
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要