Alert button
Picture for Kevin Roth

Kevin Roth

Alert button

Precise characterization of the prior predictive distribution of deep ReLU networks

Jun 11, 2021
Lorenzo Noci, Gregor Bachmann, Kevin Roth, Sebastian Nowozin, Thomas Hofmann

Figure 1 for Precise characterization of the prior predictive distribution of deep ReLU networks
Figure 2 for Precise characterization of the prior predictive distribution of deep ReLU networks
Figure 3 for Precise characterization of the prior predictive distribution of deep ReLU networks
Viaarxiv icon

Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect

Jun 11, 2021
Lorenzo Noci, Kevin Roth, Gregor Bachmann, Sebastian Nowozin, Thomas Hofmann

Figure 1 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Figure 2 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Figure 3 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Figure 4 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Viaarxiv icon

A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification

Jun 06, 2021
Kevin Roth

Figure 1 for A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification
Figure 2 for A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification
Figure 3 for A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification
Figure 4 for A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification
Viaarxiv icon

The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks

Feb 07, 2020
Jakub Swiatkowski, Kevin Roth, Bastiaan S. Veeling, Linh Tran, Joshua V. Dillon, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, Sebastian Nowozin

Figure 1 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Figure 2 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Figure 3 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Figure 4 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Viaarxiv icon

How Good is the Bayes Posterior in Deep Neural Networks Really?

Feb 06, 2020
Florian Wenzel, Kevin Roth, Bastiaan S. Veeling, Jakub Świątkowski, Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, Sebastian Nowozin

Figure 1 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Figure 2 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Figure 3 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Figure 4 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Viaarxiv icon

Hydra: Preserving Ensemble Diversity for Model Distillation

Jan 14, 2020
Linh Tran, Bastiaan S. Veeling, Kevin Roth, Jakub Swiatkowski, Joshua V. Dillon, Jasper Snoek, Stephan Mandt, Tim Salimans, Sebastian Nowozin, Rodolphe Jenatton

Figure 1 for Hydra: Preserving Ensemble Diversity for Model Distillation
Figure 2 for Hydra: Preserving Ensemble Diversity for Model Distillation
Figure 3 for Hydra: Preserving Ensemble Diversity for Model Distillation
Figure 4 for Hydra: Preserving Ensemble Diversity for Model Distillation
Viaarxiv icon

Adversarial Training Generalizes Data-dependent Spectral Norm Regularization

Jun 17, 2019
Kevin Roth, Yannic Kilcher, Thomas Hofmann

Figure 1 for Adversarial Training Generalizes Data-dependent Spectral Norm Regularization
Figure 2 for Adversarial Training Generalizes Data-dependent Spectral Norm Regularization
Figure 3 for Adversarial Training Generalizes Data-dependent Spectral Norm Regularization
Figure 4 for Adversarial Training Generalizes Data-dependent Spectral Norm Regularization
Viaarxiv icon

The Odds are Odd: A Statistical Test for Detecting Adversarial Examples

Feb 13, 2019
Kevin Roth, Yannic Kilcher, Thomas Hofmann

Figure 1 for The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Figure 2 for The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Figure 3 for The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Figure 4 for The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Viaarxiv icon

Adversarially Robust Training through Structured Gradient Regularization

May 22, 2018
Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann

Figure 1 for Adversarially Robust Training through Structured Gradient Regularization
Figure 2 for Adversarially Robust Training through Structured Gradient Regularization
Figure 3 for Adversarially Robust Training through Structured Gradient Regularization
Figure 4 for Adversarially Robust Training through Structured Gradient Regularization
Viaarxiv icon