Why Does Large Batch Training Result in Poor Generalization? A Comprehensive Explanation and a Better Strategy from the Viewpoint of Stochastic Optimization

Tomoumi Takase, Satoshi Oyama, Masahito Kurihara
  • Neural Computation, July 2018, The MIT Press
  • DOI: 10.1162/neco_a_01089
The author haven't finished explaining this publicationThe author haven't finished explaining this publication

The following have contributed to this page: Tomoumi Takase and Satoshi Oyama