research
∙
10/20/2020
Tight Second-Order Certificates for Randomized Smoothing
Randomized smoothing is a popular way of providing robustness guarantees...
share
research
∙
09/25/2019
FreeLB: Enhanced Adversarial Training for Language Understanding
Adversarial training, which minimizes the maximal risk for label-preserv...
research
∙
05/28/2019
Network Deconvolution
Convolution is a central operation in Convolutional Neural Networks (CNN...
research
∙
08/07/2016
ShapeFit and ShapeKick for Robust, Scalable Structure from Motion
We introduce a new method for location recovery from pair-wise direction...
research
∙
10/15/2015
Layer-Specific Adaptive Learning Rates for Deep Networks
The increasing complexity of deep learning architectures is resulting in...
research
∙
12/01/2014