activity
20192022
most citedGeneralized Bayesian Posterior Expectation Distillation for Deep Neural Networks

4 citations · 14 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2022

Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning

Meet P. Vadera, Adam D. Cobb, Brian Jalaian +1

Bayesian methods hold significant promise for improving the uncertainty quantification ability and robustness of deep neural network models. Recent research has seen the investigat…

cs.LG20213 cited

Post-hoc loss-calibration for Bayesian neural networks

Meet P. Vadera, Soumya Ghosh, Kenney Ng +1

Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available. Modern Bayesian models, however,…

cs.LG20204 cited

URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks

Meet P. Vadera, Adam D. Cobb, Brian Jalaian +1

While deep learning methods continue to improve in predictive accuracy on a wide range of application domains, significant issues remain with other aspects of their performance inc…

cs.LG20204 cited

Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks

Meet P. Vadera, Brian Jalaian, Benjamin M. Marlin

In this paper, we present a general framework for distilling expectations with respect to the Bayesian posterior distribution of a deep neural network classifier, extending prior w…

cs.LG20202 cited

Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification

Meet P. Vadera, Satya Narayan Shukla, Brian Jalaian +1

In this paper, we consider the problem of assessing the adversarial robustness of deep neural network models under both Markov chain Monte Carlo (MCMC) and Bayesian Dark Knowledge…

cs.LG20191 cited

Assessing the Robustness of Bayesian Dark Knowledge to Posterior Uncertainty

Meet P. Vadera, Benjamin M. Marlin

Bayesian Dark Knowledge is a method for compressing the posterior predictive distribution of a neural network model into a more compact form. Specifically, the method attempts to c…