Few-sample Variational Inference of Bayesian Neural Networks with Arbitrary Nonlinearities

arXiv:2405.02063v1 Announce Type: new
Abstract: Bayesian Neural Networks (BNNs) extend traditional neural networks to provide uncertainties associated with their outputs. On the forward pass through a BNN, predictions (and their uncertainties) are made either by Monte Carlo sampling network weights from the learned posterior or by analytically propagating statistical moments through the network. Though flexible, Monte Carlo sampling is computationally expensive and can be infeasible or impractical under resource constraints or for large networks. While moment propagation can ameliorate the …

abstract arxiv bayesian cs.lg inference moments network networks neural networks posterior predictions sample sampling statistical through type