306 citations · 1.4k across the 39 of their papers we have counts for
3 papers · 1 filter
Which Minimizer Does My Neural Network Converge To?
Manuel Nonnenmacher, David Reeb, Ingo Steinwart
The loss surface of an overparameterized neural network (NN) possesses many global minima of zero training error. We explain how common variants of the standard NN training procedu…
Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties
Jakob Lindinger, David Reeb, Christoph Lippert +1
Deep Gaussian Processes learn probabilistic data representations for supervised learning by cascading multiple Gaussian Processes. While this model family promises flexible predict…
Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds
David Reeb, Andreas Doerr, Sebastian Gerwinn +1
Gaussian Processes (GPs) are a generic modelling tool for supervised learning. While they have been successfully applied on large datasets, their use in safety-critical application…