research
∙
01/15/2019
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis
The notion of flat minima has played a key role in the generalization pr...
share
research
∙
09/11/2018
On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions
Data-agnostic quasi-imperceptible perturbations on inputs can severely d...
research
∙
02/16/2018
Variance-based Gradient Compression for Efficient Distributed Deep Learning
Due to the substantial computational cost, training state-of-the-art dee...
research
∙
02/12/2018