Web: http://arxiv.org/abs/2206.08900

June 20, 2022, 1:12 a.m. | Javier Antorán, David Janz, James Urquhart Allingham, Erik Daxberger, Riccardo Barbano, Eric Nalisnick, José Miguel Hernández-Lobato

stat.ML updates on arXiv.org arxiv.org

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 work, we
examine the assumptions behind this method, particularly in conjunction with
model selection. We show that these interact poorly with some now-standard
tools of deep learning--stochastic approximation methods and normalisation
layers--and make recommendations for how to better …

arxiv deep deep learning evidence learning ml model

More from arxiv.org / stat.ML updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY