Title | ||
---|---|---|
Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation. |
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. |
Year | Venue | Field |
---|---|---|
2019 | UAI | Computer science,Inference,Artificial intelligence,Bayesian neural networks,Sampling (statistics),Backpropagation,Machine learning |
DocType | Citations | PageRank |
Conference | 1 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Manuel Haussmann | 1 | 5 | 2.78 |
Fred A. Hamprecht | 2 | 962 | 76.24 |
Melih Kandemir | 3 | 182 | 16.91 |