AI-SARAH:自适应隐式随机递归梯度法
AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods
摘要:
我们提出了AI-SARAH,SARAH的一个实际变体。作为SARAH算法的一个变种,该算法采用随机递归梯度,但根据局部几何形状调整步长。AI-SARAH隐式计算步长,并有效地估计随机函数的局部Lipschitz光滑性。它是完全自适应的,无需调谐,实现简单,计算效率高。我们提供有关其设计和融合的技术见解和直观说明。我们进行了广泛的实证分析,并证明其强大的性能相比,其经典的同行和其他国家的最先进的一阶方法在解决凸机器学习问题。
英文摘要:
We present AI-SARAH, a practical variant of SARAH. As a variant of SARAH, this algorithm employs the stochastic recursive gradient yet adjusts step-size based on local geometry. AI-SARAH implicitly computes step-size and efficiently estimates local Lipschitz smoothness of stochastic functions. It is fully adaptive, tune-free, straightforward to implement, and computationally efficient. We provide technical insight and intuitive illustrations on its design and convergence. We conduct extensive empirical analysis and demonstrate its strong performance compared with its classical counterparts and other state-of-the-art first-order methods in solving convex machine learning problems.
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。