Reference

Laplace Redux - Effortless Bayesian Deep Learning, Erik Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig. Advances in Neural Information Processing Systems, 2021(2022)

Abstract

We argue that the Laplace approximation is a simple yet competitive and versatile method for Bayesian deep learning that deserves wider adoption. We provide a plug'n'play library for PyTorch to...