Positively Scale-Invariant Flatness of ReLU Neural Networks

6 March 2019

Papers citing "Positively Scale-Invariant Flatness of ReLU Neural Networks"

5 / 5 papers shown

Title
Local Identifiability of Deep ReLU Neural Networks: the Theory Joachim Bona-Pellissier Franccois Malgouyres F. Bachoc FAtt 67 6 0 15 Jun 2022
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction Kaifeng Lyu Zhiyuan Li Sanjeev Arora FAtt 37 69 0 14 Jun 2022
An Embedding of ReLU Networks and an Analysis of their Identifiability Pierre Stock Rémi Gribonval 28 17 0 20 Jul 2021
The Representation Theory of Neural Networks M. Armenta Pierre-Marc Jodoin 19 30 0 23 Jul 2020
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