
Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Bayesian Neural Networks (BNNs) place priors over the parameters in a ne...
read it

Fixing Variational Bayes: Deterministic Variational Inference for Bayesian Neural Networks
Bayesian neural networks (BNNs) hold great promise as a flexible and pri...
read it

A statistical theory of cold posteriors in deep neural networks
To get Bayesian neural networks to perform comparably to standard neural...
read it

URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks
While deep learning methods continue to improve in predictive accuracy o...
read it

The Case for Bayesian Deep Learning
The key distinguishing property of a Bayesian approach is marginalizatio...
read it

Using bagged posteriors for robust inference and model criticism
Standard Bayesian inference is known to be sensitive to model misspecifi...
read it

Empirical confidence estimates for classification by deep neural networks
How well can we estimate the probability that the classification, C(f(x)...
read it
How Good is the Bayes Posterior in Deep Neural Networks Really?
During the past five years the Bayesian deep learning community has developed increasingly accurate and efficient approximate inference procedures that allow for Bayesian inference in deep neural networks. However, despite this algorithmic progress and the promise of improved uncertainty quantification and sample efficiency there are—as of early 2020—no publicized deployments of Bayesian neural networks in industrial practice. 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. Furthermore, we demonstrate that predictive performance is improved significantly through the use of a "cold posterior" that overcounts evidence. Such cold posteriors sharply deviate from the Bayesian paradigm but are commonly used as heuristic in Bayesian deep learning papers. We put forward several hypotheses that could explain cold posteriors and evaluate the hypotheses through experiments. Our work questions the goal of accurate posterior approximations in Bayesian deep learning: If the true Bayes posterior is poor, what is the use of more accurate approximations? Instead, we argue that it is timely to focus on understanding the origin of the improved performance of cold posteriors.
READ FULL TEXT
Comments
There are no comments yet.