2022
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Javier Antoran, David Janz, James U Allingham, Erik Daxberger, Riccardo Rb Barbano, Eric Nalisnick +1
ICML 2022spotlight
The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community. The method provides reliable error bars and admits a closed-form expression for the model evidence, allowing for scalable selection of model hyperparameters. In this…