15 citations · 25 across the 8 of their papers we have counts for
4 papers · 1 filter
Variational Deep Learning via Implicit Regularization
Jonathan Wenger, Beau Coker, Juraj Marusic +1
Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theor…
Wide Mean-Field Bayesian Neural Networks Ignore the Data
Beau Coker, Wessel P. Bruinsma, David R. Burt +2
Bayesian neural networks (BNNs) combine the expressive power of deep learning with the advantages of Bayesian formalism. In recent years, the analysis of wide, deep BNNs has provid…
Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
Beau Coker, Weiwei Pan, Finale Doshi-Velez
Variational inference enables approximate posterior inference of the highly over-parameterized neural networks that are popular in modern machine learning. Unfortunately, such post…
Towards Expressive Priors for Bayesian Neural Networks: Poisson Process Radial Basis Function Networks
Beau Coker, Melanie F. Pradier, Finale Doshi-Velez
While Bayesian neural networks have many appealing characteristics, current priors do not easily allow users to specify basic properties such as expected lengthscale or amplitude v…