research
∙
10/05/2020
Adversarial Boot Camp: label free certified robustness in one epoch
Machine learning models are vulnerable to adversarial attacks. One appro...
share
research
∙
06/10/2020
Deterministic Gaussian Averaged Neural Networks
We present a deterministic method to compute the Gaussian average of neu...
research
∙
06/10/2020
Learning normalizing flows from Entropy-Kantorovich potentials
We approach the problem of learning continuous normalizing flows from a ...
research
∙
02/07/2020
How to train your neural ODE
Training neural ODEs on large datasets has not been tractable due to the...
research
∙
10/04/2019
Farkas layers: don't shift the data, fix the geometry
Successfully training deep neural networks often requires either batch n...
research
∙
10/03/2019
Partial differential equation regularization for supervised machine learning
This article is an overview of supervised machine learning problems for ...
research
∙
05/27/2019
Scaleable input gradient regularization for adversarial robustness
Input gradient regularization is not thought to be an effective means fo...
research
∙
03/25/2019
The LogBarrier adversarial attack: making effective use of decision boundary information
Adversarial attacks for image classification are small perturbations to ...
research
∙
03/21/2019
Empirical confidence estimates for classification by deep neural networks
How well can we estimate the probability that the classification, C(f(x)...
research
∙
08/28/2018
Lipschitz regularized Deep Neural Networks converge and generalize
Lipschitz regularized neural networks augment the usual fidelity term us...
research
∙
08/15/2016