A Survey of Algorithms and Analysis for Stochastic Gradient Methods

碩士 === 國立交通大學 === 應用數學系數學建模與科學計算碩士班 === 106 === In this thesis, we give a survey of the variant algorithms for stochastic gradient methods, including Stochastic Newton methods (SN), Stochastic Variance Reduced Gradient method (SVRG), and Adam. There are two main categories of the stochastic gradient...

Full description

Bibliographic Details
Main Authors: Syu, Jian-Ping, 許建平
Other Authors: Lee, Yuh-Jye
Format: Others
Language:en_US
Published: 2018
Online Access:http://ndltd.ncl.edu.tw/handle/a555t4