Sampling-free variational inference of Bayesian neural networks by variance backpropagation
dc.contributor.author | Haußmann, M. | |
dc.contributor.author | Hamprecht, F. A. | |
dc.contributor.author | Kandemir, Melih | |
dc.date.accessioned | 2020-10-22T10:38:18Z | |
dc.date.available | 2020-10-22T10:38:18Z | |
dc.date.issued | 2019 | |
dc.identifier.uri | http://hdl.handle.net/10679/7039 | |
dc.identifier.uri | https://auai.org/uai2019/accepted.php | |
dc.description.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. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Association For Uncertainty in Artificial Intelligence (AUAI) | en_US |
dc.relation.ispartof | 35th Conference on Uncertainty in Artificial Intelligence, UAI 2019 | |
dc.rights | restrictedAccess | |
dc.title | Sampling-free variational inference of Bayesian neural networks by variance backpropagation | en_US |
dc.type | Conference paper | en_US |
dc.publicationstatus | Published | en_US |
dc.contributor.department | Özyeğin University | |
dc.contributor.authorID | (ORCID 0000-0001-6293-3656 & YÖK ID 258737) Kandemir, Melih | |
dc.identifier.scopus | SCOPUS:2-s2.0-85084012503 | |
dc.relation.publicationcategory | Conference Paper - International - Institutional Academic Staff |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
Share this page