Philipp Hennig

research

∙ 06/13/2023

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions

Inference and simulation in the context of high-dimensional dynamical sy...

0 Jonathan Schmidt, et al. ∙

research

∙ 06/12/2023

Benchmarking Neural Network Training Algorithms

Training algorithms, broadly construed, are an essential part of every d...

6 George E. Dahl, et al. ∙

research

∙ 05/24/2023

Probabilistic Exponential Integrators

Probabilistic solvers provide a flexible and efficient framework for sim...

0 Nathanael Bosch, et al. ∙

research

∙ 05/22/2023

Uncertainty and Structure in Neural Ordinary Differential Equations

Neural ordinary differential equations (ODEs) are an emerging class of d...

0 Katharina Ott, et al. ∙

research

∙ 05/22/2023

Bayesian Numerical Integration with Neural Networks

Bayesian probabilistic numerical methods for numerical integration offer...

0 Katharina Ott, et al. ∙

research

∙ 02/14/2023

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

Model reparametrization – transforming the parameter space via a bijecti...

0 Agustinus Kristiadi, et al. ∙

research

∙ 12/23/2022

Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers

Linear partial differential equations (PDEs) are an important, widely ap...

10 Marvin Pförtner, et al. ∙

research

∙ 08/02/2022

Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs

Neural operators are a type of deep architecture that learns to solve (i...

0 Emilia Magnani, et al. ∙

research

∙ 05/30/2022

Posterior and Computational Uncertainty in Gaussian Processes

Gaussian processes scale prohibitively with the size of the dataset. In ...

9 Jonathan Wenger, et al. ∙

research

∙ 05/20/2022

Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks

Monte Carlo (MC) integration is the de facto method for approximating th...

0 Agustinus Kristiadi, et al. ∙

research

∙ 05/16/2022

Wasserstein t-SNE

Scientific datasets often have hierarchical structure: for example, in s...

0 Fynn Bachmann, et al. ∙

research

∙ 03/07/2022

Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference

Full Bayesian posteriors are rarely analytically tractable, which is why...

0 Luca Rendsburg, et al. ∙

research

∙ 02/02/2022

Fenrir: Physics-Enhanced Regression for Initial Value Problems

We show how probabilistic numerics can be used to convert an initial val...

0 Filip Tronarp, et al. ∙

research

∙ 12/03/2021

ProbNum: Probabilistic Numerics in Python

Probabilistic numerical methods (PNMs) solve numerical problems via prob...

6 Jonathan Wenger, et al. ∙

research

∙ 11/05/2021

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

Deep neural networks are prone to overconfident predictions on outliers....

0 Runa Eschenhagen, et al. ∙

research

∙ 10/22/2021

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

This work develops a class of probabilistic algorithms for the numerical...

0 Nicholas Krämer, et al. ∙

research

∙ 10/22/2021

Probabilistic ODE Solutions in Millions of Dimensions

Probabilistic solvers for ordinary differential equations (ODEs) have em...

0 Nicholas Krämer, et al. ∙

research

∙ 10/20/2021

Pick-and-Mix Information Operators for Probabilistic ODE Solvers

Probabilistic numerical solvers for ordinary differential equations comp...

0 Nathanael Bosch, et al. ∙

research

∙ 07/01/2021

Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning

Gaussian processes remain popular as a flexible and expressive model cla...

7 Jonathan Wenger, et al. ∙

research

∙ 06/28/2021

Laplace Redux – Effortless Bayesian Deep Learning

Bayesian formulations of deep learning have been shown to have compellin...

0 Erik Daxberger, et al. ∙

research

∙ 06/18/2021

Being a Bit Frequentist Improves Bayesian Neural Networks

Despite their compelling theoretical properties, Bayesian neural network...

0 Agustinus Kristiadi, et al. ∙

research

∙ 06/14/2021

Linear-Time Probabilistic Solutions of Boundary Value Problems

We propose a fast algorithm for the probabilistic solution of boundary v...

0 Nicholas Krämer, et al. ∙

research

∙ 06/04/2021

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

Curvature in form of the Hessian or its generalized Gauss-Newton (GGN) a...

0 Felix Dangel, et al. ∙

research

∙ 05/13/2021

Informed Equation Learning

Distilling data into compact and interpretable analytic equations is one...

0 Matthias Werner, et al. ∙

research

∙ 05/07/2021

Laplace Matching for fast Approximate Inference in Generalized Linear Models

Bayesian inference in generalized linear models (GLMs), i.e. Gaussian re...

0 Marius Hobbhahn, et al. ∙

research

∙ 03/18/2021

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

Mechanistic models with differential equations are a key component of sc...

0 Jonathan Schmidt, et al. ∙

research

∙ 02/22/2021

A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization

Machine learning practitioners invest significant manual and computation...

0 Filip de Roos, et al. ∙

research

∙ 02/15/2021

High-Dimensional Gaussian Process Inference with Derivatives

Although it is widely known that Gaussian processes can be conditioned o...

0 Filip de Roos, et al. ∙

research

∙ 02/12/2021

Bayesian Quadrature on Riemannian Data Manifolds

Riemannian manifolds provide a principled way to model nonlinear geometr...

14 Christian Fröhlich, et al. ∙

research

∙ 02/12/2021

Cockpit: A Practical Debugging Tool for Training Deep Neural Networks

When engineers train deep learning models, they are very much "flying bl...

76 Frank Schneider, et al. ∙

research

∙ 12/18/2020

Stable Implementation of Probabilistic ODE Solvers

Probabilistic solvers for ordinary differential equations (ODEs) provide...

0 Nicholas Krämer, et al. ∙

research

∙ 12/15/2020

Calibrated Adaptive Probabilistic ODE Solvers

Probabilistic solvers for ordinary differential equations (ODEs) assign ...

12 Nathanael Bosch, et al. ∙

research

∙ 11/09/2020

Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering

Standard first-order stochastic optimization algorithms base their updat...

0 Ricky T. Q. Chen, et al. ∙

research

∙ 10/19/2020

Probabilistic Linear Solvers for Machine Learning

Linear systems are the bedrock of virtually all numerical computation. M...

19 Jonathan Wenger, et al. ∙

research

∙ 10/16/2020

Robot Learning with Crash Constraints

In the past decade, numerous machine learning algorithms have been shown...

0 Alonso Marco, et al. ∙

research

∙ 10/06/2020

Learnable Uncertainty under Laplace Approximations

Laplace approximations are classic, computationally lightweight means fo...

0 Agustinus Kristiadi, et al. ∙

research

∙ 10/06/2020

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features

Approximate Bayesian methods can mitigate overconfidence in ReLU network...

2 Agustinus Kristiadi, et al. ∙

research

∙ 07/30/2020

When are Neural ODE Solutions Proper ODEs?

A key appeal of the recently proposed Neural Ordinary Differential Equat...

10 Katharina Ott, et al. ∙

research

∙ 07/03/2020

Descending through a Crowded Valley – Benchmarking Deep Learning Optimizers

Choosing the optimizer is among the most crucial decisions of deep learn...

7 Robin M. Schmidt, et al. ∙

research

∙ 04/01/2020

Bayesian ODE Solvers: The Maximum A Posteriori Estimate

It has recently been established that the numerical solution of ordinary...

40 Filip Tronarp, et al. ∙

research

∙ 03/02/2020

Fast Predictive Uncertainty for Classification with Bayesian Deep Networks

In Bayesian Deep Learning, distributions over the output of classificati...

10 Marius Hobbhahn, et al. ∙

research

∙ 02/24/2020

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks

The point estimates of ReLU classification networks—arguably the most wi...

0 Agustinus Kristiadi, et al. ∙

research

∙ 02/21/2020

Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems

Likelihood-free (a.k.a. simulation-based) inference problems are inverse...

0 Hans Kersting, et al. ∙

research

∙ 12/23/2019

BackPACK: Packing more into backprop

Automatic differentiation frameworks are optimized for exactly one thing...

10 Felix Dangel, et al. ∙

research

∙ 11/14/2019

Conjugate Gradients for Kernel Machines

Regularized least-squares (kernel-ridge / Gaussian process) regression i...

41 Simon Bartels, et al. ∙

research

∙ 10/21/2019

Integrals over Gaussians under Linear Domain Constraints

Integrals of linearly constrained multivariate Gaussian densities are a ...

0 Alexandra Gessner, et al. ∙

research

∙ 07/24/2019

Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties

Learning robot controllers by minimizing a black-box objective cost usin...

3 Alonso Marco, et al. ∙

research

∙ 06/27/2019

Uncertainty Estimates for Ordinal Embeddings

To investigate objects without a describable notion of distance, one can...

5 Michael Lohaus, et al. ∙

research

∙ 05/29/2019

Limitations of the Empirical Fisher Approximation

Natural gradient descent, which preconditions a gradient descent update ...

0 Frederik Kunstner, et al. ∙

research

∙ 05/24/2019

Convergence Guarantees for Adaptive Bayesian Quadrature Methods

Adaptive Bayesian quadrature (ABQ) is a powerful approach to numerical i...

0 Motonobu Kanagawa, et al. ∙

Philipp Hennig

Featured Co-authors