Stochasticity of Deterministic Gradient Descent:
Large Learning Rate for Multiscale Objective Function
Lingkai Kong Molei Tao
School of Mathematics School of Mathematics
University of Science and Technology of China Georgia Institute of Technology
and Georgia Institute of Technology mtao@gatech.edu
Abstract
This article suggests that deterministic Gradient Descent, which ...


雷达卡


京公网安备 11010802022788号







