no code implementations • 5 Jun 2024 • Hrittik Roy, Marco Miani, Carl Henrik Ek, Philipp Hennig, Marvin Pförtner, Lukas Tatzel, Søren Hauberg
Current approximate posteriors in Bayesian neural networks (BNNs) exhibit a crucial limitation: they fail to maintain invariance under reparameterization, i. e. BNNs assign different posterior densities to different parametrizations of identical functions.
1 code implementation • 27 May 2024 • Nicholas Krämer, Pablo Moreno-Muñoz, Hrittik Roy, Søren Hauberg
Tuning scientific and probabilistic machine learning models -- for example, partial differential equations, Gaussian processes, or Bayesian neural networks -- often relies on evaluating functions of matrices whose size grows with the data set or the number of parameters.
no code implementations • 10 Jul 2023 • Alison Pouplin, Hrittik Roy, Sidak Pal Singh, Georgios Arvanitidis
In this work, we consider the loss landscape as an embedded Riemannian manifold and show that the differential geometric properties of the manifold can be used when analyzing the generalization abilities of a deep net.