MIA: Andrew Gordon Wilson on Bayesian deep learning; Primer: Pavel Izmailov and Polina Kirichenko

Models, Inference and Algorithms October 30, 2019 Meeting: Loss Valleys, Uncertainty, and Generalization in Deep Learning Andrew Gordon Wilson Courant Institute, NYU In this talk we discuss how to exploit the geometry of training objectives for scalable Bayesian model averaging, leading to better point predictions, as well as uncertainty and calibration in deep learning. We will focus primarily on five works, which include the s