PAGE: A Simple and Optimal Probabilistic Gradient Estimator for
Nonconvex Optimization
Zhize Li 1 Hongyan Bao 1 Xiangliang Zhang 1 Peter Richtarik 1
Abstract (Jain & Kar, 2017). Driven by the applied success of deep
neural networks (LeCun et al., 2015), and the critical place
In this paper, we propose a novel stochastic gradi-
nonconvex optimization plays in training ...


雷达卡




京公网安备 11010802022788号







