Sampling-free variational inference of Bayesian neural networks by variance backpropagation
Type :
Conference paper
Publication Status :
Published
Access :
restrictedAccess
Abstract
We propose a new Bayesian Neural Net formulation that affords variational inference for which the evidence lower bound is analytically tractable subject to a tight approximation. We achieve this tractability by (i) decomposing ReLU nonlinearities into the product of an identity and a Heaviside step function, (ii) introducing a separate path that decomposes the neural net expectation from its variance. We demonstrate formally that introducing separate latent binary variables to the activations allows representing the neural network likelihood as a chain of linear operations. Performing variational inference on this construction enables a sampling-free computation of the evidence lower bound which is a more effective approximation than the widely applied Monte Carlo sampling and CLT related techniques. We evaluate the model on a range of regression and classification tasks against BNN inference alternatives, showing competitive or improved performance over the current state-of-the-art.
Source :
35th Conference on Uncertainty in Artificial Intelligence, UAI 2019
Date :
2019
Publisher :
Association For Uncertainty in Artificial Intelligence (AUAI)
Collections
Share this page