The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?

10 May 2019

Papers citing "The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?"

1 / 1 papers shown

Title
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 281 2,889 0 15 Sep 2016