Projected BNNs: Avoiding weight-space pathologies by learning latent
representations of neural network weights

Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

16 November 2018

Melanie F. Pradier

Finale Doshi-velez

Papers citing "Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights"

5 / 5 papers shown

Title
Implicit Variational Inference for High-Dimensional Posteriors Anshuk Uppal Kristoffer Stensbo-Smidt Wouter Boomsma J. Frellsen BDL 26 1 0 10 Oct 2023
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences Daniel S. Brown Russell Coleman R. Srinivasan S. Niekum BDL 30 101 0 21 Feb 2020
Subspace Inference for Bayesian Deep Learning Pavel Izmailov Wesley J. Maddox Polina Kirichenko T. Garipov Dmitry Vetrov A. Wilson UQCV BDL 38 142 0 17 Jul 2019
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,661 0 05 Dec 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,138 0 06 Jun 2015