Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks

Yoav Gelberg, Tycho F. A. van der Ouderaa, Mark van der Wilk +1

Weight space symmetries in neural network architectures, such as permutation symmetries in MLPs, give rise to Bayesian neural network (BNN) posteriors with many equivalent modes. T…