Search Results for author:
Found 12 papers, 4 papers with code
Precise characterization of the prior predictive distribution of deep ReLU networks
Recent works on Bayesian neural networks (BNNs) have highlighted the need to better understand the implications of using Gaussian priors in combination with the compositional structure of the network architecture.
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
The dataset curation hypothesis of Aitchison (2020): we show empirically that the CPE does not arise in a real curated data set but can be produced in a controlled experiment with varying curation strength.
A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification
This approach is however inherently limited, as it says little about the robustness of the model against more powerful attacks not included in the evaluation.
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 approximating posterior distributions over Bayesian neural network weights.
How Good is the Bayes Posterior in Deep Neural Networks Really?
In this work we cast doubt on the current understanding of Bayes posteriors in popular deep neural networks: we demonstrate through careful MCMC sampling that the posterior predictive induced by the Bayes posterior yields systematically worse predictions compared to simpler methods including point estimates obtained from SGD.
Hydra: Preserving Ensemble Diversity for Model Distillation
As a result, the diversity of the ensemble predictions, stemming from each member, is lost.
On the Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Variational Bayesian Inference is a popular methodology for approximating posterior distributions in Bayesian neural networks.
Adversarial Training Generalizes Data-dependent Spectral Norm Regularization
We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks.
Adversarial Training is a Form of Data-dependent Operator Norm Regularization
We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks.
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
We investigate conditions under which test statistics exist that can reliably detect examples, which have been adversarially manipulated in a white-box attack.
Adversarially Robust Training through Structured Gradient Regularization
We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations.
Stabilizing Training of Generative Adversarial Networks through Regularization
Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters.
