214 citations · 1.8k across the 88 of their papers we have counts for
4 papers · 2 filters
Stable Implementation of Probabilistic ODE Solvers
Nicholas Krämer, Philipp Hennig
Probabilistic solvers for ordinary differential equations (ODEs) provide efficient quantification of numerical uncertainty associated with simulation of dynamical systems. Their co…
Doubly infinite residual neural networks: a diffusion process approach
Stefano Peluchetti, Stefano Favaro
Modern neural networks (NN) featuring a large number of layers (depth) and units per layer (width) have achieved a remarkable performance across many domains. While there exists a…
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
Agustinus Kristiadi, Matthias Hein, Philipp Hennig
The point estimates of ReLU classification networks---arguably the most widely used neural network architecture---have been shown to yield arbitrarily high confidence far away from…
Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems
Hans Kersting, Nicholas Krämer, Martin Schiegg +3
Likelihood-free (a.k.a. simulation-based) inference problems are inverse problems with expensive, or intractable, forward models. ODE inverse problems are commonly treated as likel…