Adapting the Linearised Laplace Model Evidence for Modern Deep Learning

Javier Antorán, David Janz, James Urquhart Allingham, Erik A. Daxberger, Riccardo Barbano, Eric T. Nalisnick, José Miguel Hernández-Lobato

Abstract: 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-fo...