Publications

Antonio Orvieto, Anant Raj, Hans Kersting, Francis Bach (2022). Explicit Regularization in Overparametrized Models via Noise Injection. arXiv.

PDF arXiv

Philipp Hennig, Michael A. Osborne, Hans Kersting (2022). Probabilistic Numerics - Computation as Machine Learning. Cambridge University Press.

Cambridge book

Antonio Orvieto, Hans Kersting, Frank Proske, Francis Bach, Aurelien Lucchi (2022). Anticorrelated Noise Injection for Improved Generalization. ICML 2022.

PDF arXiv

Hans Kersting (2021). Uncertainty-Aware Numerical Solutions of ODEs by Bayesian Filtering. Eberhard Karls Universität Tübingen.

PDF Uni Tübingen

Hans Kersting, Tim J. Sullivan, Philipp Hennig (2020). Convergence Rates of Gaussian ODE Filters. Statistics and Computing.

PDF arXiv Proceedings

Hans Kersting, Maren Mahsereci (2020). A Fourier State Space Model for Bayesian ODE Filters. INNF+ Workshop, ICML 2020.

PDF arXiv

Hans Kersting, Nicholas Krämer, Martin Schiegg, Christian Daniel, Michael Tiemann, Philipp Hennig (2020). Differentiable Likelihoods for Fast Inversion of ‘Likelihood-Free’ Dynamical Systems. ICML 2020.

PDF Slides Video arXiv Proceedings

Filip Tronarp, Hans Kersting, Simo Särkkä, Philipp Hennig (2019). Probabilistic Solutions to Ordinary Differential Equations as Non-Linear Bayesian Filtering: A New Perspective. Statistics and Computing.

PDF arXiv journal

Emilia Magnani, Hans Kersting, Michael Schober, Philipp Hennig (2017). Bayesian Filtering for ODEs with Bounded Derivatives. arXiv.

PDF arXiv

Hans Kersting, Philipp Hennig (2016). Active Uncertainty Calibration in Bayesian ODE Solvers. UAI 2016.

PDF arXiv Proceedings