Lune

Profiles2020-2024

Philipp Hennig

Tübingen AI Center, University of Tübingen

12Papers
7Last author
22Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers12

  1. Reparameterization invariance in approximate Bayesian inferenceAuthor 4 of 7NeurIPS 2024 · 20 citations
  2. FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep LearningAuthor 6 of 7NeurIPS 2024 · 15 citations
  3. The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High DimensionsAuthor 2 of 4NeurIPS 2023 · 22 citations
  4. The Geometry of Neural Nets' Parameter Spaces Under ReparametrizationAuthor 3 of 3NeurIPS 2023 · 21 citations
  5. Probabilistic Exponential IntegratorsAuthor 2 of 3NeurIPS 2023 · 7 citations
  6. Posterior Refinement Improves Sample Efficiency in Bayesian Neural NetworksAuthor 3 of 3NeurIPS 2022 · 17 citations
  7. ResNet After All: Neural ODEs and Their Numerical SolutionAuthor 3 of 4ICLR 2021 · 34 citations
  8. A Probabilistic State Space Model for Joint Inference from Differential Equations and DataAuthor 3 of 3NeurIPS 2021 · 30 citations
  9. Cockpit: A Practical Debugging Tool for the Training of Deep Neural NetworksAuthor 3 of 3NeurIPS 2021 · 14 citations
  10. An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic OverconfidenceAuthor 3 of 3NeurIPS 2021 · 10 citations
  11. Linear-Time Probabilistic Solution of Boundary Value ProblemsAuthor 2 of 2NeurIPS 2021 · 8 citations
  12. Probabilistic Linear Solvers for Machine LearningAuthor 2 of 2NeurIPS 2020 · 19 citations
Dusk over the sea between two cliffs drawn in fine vertical lines