The StochAstic Recursive grAdient algoritHm (SARAH) algorithm is a variance reduced variant of the Stochastic Gradient Descent algorithm that needs a gradient of the objective function from time to time. In this paper, we remove the necessity of a full gradient computation. This is achieved by using a randomized reshuffling strategy and aggregating stochastic gradients obtained in each epoch. The aggregated stochastic gradients serve as an estimate of a full gradient in the SARAH algorithm. We provide a theoretical analysis of the proposed approach and conclude the paper with numerical experiments that demonstrate the efficiency of this approach.

中文翻译：

---

随机重新洗牌的 SARAH 不需要完整的梯度计算

随机递归梯度算法 (SARAH) 算法是随机梯度下降算法的方差减小变体，它时常需要目标函数的梯度。在本文中，我们消除了完整梯度计算的必要性。这是通过使用随机重组策略并聚合每个时期获得的随机梯度来实现的。聚合的随机梯度用作 SARAH 算法中完整梯度的估计。我们对所提出的方法进行了理论分析，并通过数值实验来总结本文，证明了该方法的效率。