-
Precise characterization of the prior predictive distribution of deep ReLU networks
Recent works on Bayesian neural networks (BNNs) have highlighted the nee...
06/11/2021 ∙ by Lorenzo Noci, et al. ∙
0
∙
share
read it
-
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
The "cold posterior effect" (CPE) in Bayesian deep learning describes th...
06/11/2021 ∙ by Lorenzo Noci, et al. ∙
0
∙
share
read it
-
A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification
The existence of adversarial examples poses a real danger when deep neur...
06/06/2021 ∙ by Kevin Roth, et al. ∙
0
∙
share
read it
-
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Variational Bayesian Inference is a popular methodology for approximatin...
02/07/2020 ∙ by Jakub Świątkowski, et al. ∙
6
∙
share
read it
-
How Good is the Bayes Posterior in Deep Neural Networks Really?
During the past five years the Bayesian deep learning community has deve...
02/06/2020 ∙ by Florian Wenzel, et al. ∙
27
∙
share
read it
-
Hydra: Preserving Ensemble Diversity for Model Distillation
Ensembles of models have been empirically shown to improve predictive pe...
01/14/2020 ∙ by Linh Tran, et al. ∙
1
∙
share
read it
-
Adversarial Training Generalizes Data-dependent Spectral Norm Regularization
We establish a theoretical link between adversarial training and operato...
06/04/2019 ∙ by Kevin Roth, et al. ∙
12
∙
share
read it
-
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
We investigate conditions under which test statistics exist that can rel...
02/13/2019 ∙ by Kevin Roth, et al. ∙
18
∙
share
read it
-
Adversarially Robust Training through Structured Gradient Regularization
We propose a novel data-dependent structured gradient regularizer to inc...
05/22/2018 ∙ by Kevin Roth, et al. ∙
2
∙
share
read it
-
Stabilizing Training of Generative Adversarial Networks through Regularization
Deep generative models based on Generative Adversarial Networks (GANs) h...
05/25/2017 ∙ by Kevin Roth, et al. ∙
0
∙
share
read it
