Variational Laplace for Bayesian neural networks
We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-network weights. The Variational Laplace objective is simple to evaluate, as it is (in essence) the log-likelihood, plus weight-decay, plus a squared-gradient regularizer. Variational Laplace gave better test performance and expected calibration errors than maximum a-posteriori inference and standard sampling-based variational inference, despite using the same variational approximate posterior. Finally, we emphasise care needed in benchmarking standard VI as there is a risk of stopping before the variance parameters have converged. We show that early-stopping can be avoided by increasing the learning rate for the variance parameters.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingImage ClassificationVariational InferenceSimilar Papers 제목 키워드 기반
Variational Laplace for Bayesian neural networks
We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-netwo…
BenchmarkingVariational InferenceThe variational Laplace approach to approximate Bayesian inference
Variational approaches to approximate Bayesian inference provide very efficient means of performing parameter estimation and model selection. Among these, so-called variational-Laplace or VL schemes rely on Gaussian appr…
Bayesian InferenceModel Selectionparameter estimationDisentangling the Gauss-Newton Method and Approximate Inference for Neural Networks
In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian dee…
Deep LearningGaussian ProcessesIntegrated Non-Factorized Variational Inference
We present a non-factorized variational method for full posterior inference in Bayesian hierarchical models, with the goal of capturing the posterior variable dependencies via efficient and possibly parallel computation…
Variational InferenceMixed Variational Inference
The Laplace approximation has been one of the workhorses of Bayesian inference. It often delivers good approximations in practice despite the fact that it does not strictly take into account where the volume of posterior…
Bayesian InferenceVariational Inference