Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Philipp Hennig

ProbNum: Probabilistic Numerics in Python


Dec 03, 2021
Jonathan Wenger, Nicholas KrÀmer, Marvin Pförtner, Jonathan Schmidt, Nathanael Bosch, Nina Effenberger, Johannes Zenn, Alexandra Gessner, Toni Karvonen, François-Xavier Briol, Maren Mahsereci, Philipp Hennig


  Access Paper or Ask Questions

Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning


Nov 05, 2021
Runa Eschenhagen, Erik Daxberger, Philipp Hennig, Agustinus Kristiadi

* Bayesian Deep Learning Workshop, NeurIPS 2021 

  Access Paper or Ask Questions

Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations


Oct 22, 2021
Nicholas KrÀmer, Jonathan Schmidt, Philipp Hennig


  Access Paper or Ask Questions

Probabilistic ODE Solutions in Millions of Dimensions


Oct 22, 2021
Nicholas KrÀmer, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig


  Access Paper or Ask Questions

Pick-and-Mix Information Operators for Probabilistic ODE Solvers


Oct 20, 2021
Nathanael Bosch, Filip Tronarp, Philipp Hennig

* 13 pages, 7 figures 

  Access Paper or Ask Questions

Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning


Jul 01, 2021
Jonathan Wenger, Geoff Pleiss, Philipp Hennig, John P. Cunningham, Jacob R. Gardner


  Access Paper or Ask Questions

Laplace Redux -- Effortless Bayesian Deep Learning


Jun 28, 2021
Erik Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig

* Source Code: https://github.com/AlexImmer/Laplace; Library Documentation: https://aleximmer.github.io/Laplace/ 

  Access Paper or Ask Questions

Being a Bit Frequentist Improves Bayesian Neural Networks


Jun 18, 2021
Agustinus Kristiadi, Matthias Hein, Philipp Hennig


  Access Paper or Ask Questions

Probabilistic DAG Search


Jun 16, 2021
Julia Grosse, Cheng Zhang, Philipp Hennig

* 10 pages, 8 figures, to be published at the Conference on Uncertainty in Artificial Intelligence (UAI) 2021 

  Access Paper or Ask Questions

Linear-Time Probabilistic Solutions of Boundary Value Problems


Jun 14, 2021
Nicholas KrÀmer, Philipp Hennig


  Access Paper or Ask Questions

ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure


Jun 04, 2021
Felix Dangel, Lukas Tatzel, Philipp Hennig

* Main text: 11 pages, 3 figures; Supplements: 14 pages, 10 figures, 2 tables 

  Access Paper or Ask Questions

Informed Equation Learning


May 13, 2021
Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius


  Access Paper or Ask Questions

Laplace Matching for fast Approximate Inference in Generalized Linear Models


May 07, 2021
Marius Hobbhahn, Philipp Hennig

* Currently under review at JMLR 

  Access Paper or Ask Questions

A Probabilistic State Space Model for Joint Inference from Differential Equations and Data


Mar 18, 2021
Jonathan Schmidt, Nicholas KrÀmer, Philipp Hennig

* 10 pages (+ 6 pages supplementary material), 6 figures 

  Access Paper or Ask Questions

A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization


Feb 22, 2021
Filip de Roos, Carl Jidling, Adrian Wills, Thomas Schön, Philipp Hennig


  Access Paper or Ask Questions

High-Dimensional Gaussian Process Inference with Derivatives


Feb 15, 2021
Filip de Roos, Alexandra Gessner, Philipp Hennig


  Access Paper or Ask Questions

Bayesian Quadrature on Riemannian Data Manifolds


Feb 12, 2021
Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis


  Access Paper or Ask Questions

Cockpit: A Practical Debugging Tool for Training Deep Neural Networks


Feb 12, 2021
Frank Schneider, Felix Dangel, Philipp Hennig

* Main text: 10 pages, 7 figures, 1 table; Supplements: 17 pages, 9 figures, 1 table 

  Access Paper or Ask Questions

Stable Implementation of Probabilistic ODE Solvers


Dec 18, 2020
Nicholas KrÀmer, Philipp Hennig


  Access Paper or Ask Questions

Calibrated Adaptive Probabilistic ODE Solvers


Dec 15, 2020
Nathanael Bosch, Philipp Hennig, Filip Tronarp

* 17 pages, 10 figures 

  Access Paper or Ask Questions

Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering


Nov 09, 2020
Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig


  Access Paper or Ask Questions

Probabilistic Linear Solvers for Machine Learning


Oct 22, 2020
Jonathan Wenger, Philipp Hennig

* Advances in Neural Information Processing Systems (NeurIPS 2020) 

  Access Paper or Ask Questions

Robot Learning with Crash Constraints


Oct 16, 2020
Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe

* 8 pages, 5 figures, 1 table, 1 algorithm. Under review. Video demonstration of the experiments available at https://youtu.be/RAiIo0l6_rE . Algorithm implementation available at https://github.com/alonrot/classified_regression.git 

  Access Paper or Ask Questions

Learnable Uncertainty under Laplace Approximations


Oct 06, 2020
Agustinus Kristiadi, Matthias Hein, Philipp Hennig


  Access Paper or Ask Questions

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features


Oct 06, 2020
Agustinus Kristiadi, Matthias Hein, Philipp Hennig


  Access Paper or Ask Questions

When are Neural ODE Solutions Proper ODEs?


Jul 30, 2020
Katharina Ott, Prateek Katiyar, Philipp Hennig, Michael Tiemann


  Access Paper or Ask Questions

Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers


Jul 07, 2020
Robin M. Schmidt, Frank Schneider, Philipp Hennig

* For the raw results, please see https://github.com/SirRob1997/Descending-through-a-Crowded-Valley---Results v2: Removed LaTeX artifacts in title 

  Access Paper or Ask Questions

Descending through a Crowded Valley -- Benchmarking Deep Learning Optimizers


Jul 03, 2020
Robin M. Schmidt, Frank Schneider, Philipp Hennig

* For the raw results, please see https://github.com/SirRob1997/Descending-through-a-Crowded-Valley---Results 

  Access Paper or Ask Questions

Bayesian ODE Solvers: The Maximum A Posteriori Estimate


Apr 01, 2020
Filip Tronarp, Simo Sarkka, Philipp Hennig


  Access Paper or Ask Questions