Philipp Hennig
80 publications
10 venues
H Index 21
Affiliation
University of T bingen, Department of Computer Science, GermanyMax Planck Institute for Intelligent Systems, T bingen, Germany
University of Cambridge, UK
Links
DBLPGoogle Scholar
Twitter- https://uni-tuebingen.de/en/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/methoden-des-maschinellen-lernens/personen/philipp-hennig/
- https://pn.is.tuebingen.mpg.de/person/phennig
- https://openreview.net/profile?id=~Philipp_Hennig1
- https://orcid.org/0000-0001-7293-6092
- https://www.wikidata.org/entity/Q61053304
- https://d-nb.info/gnd/1178518078
- https://mathgenealogy.org/id.php?id=240325
| Name | Venue | Year | citations |
|---|---|---|---|
Accelerating neural network training: An analysis of the AlgoPerf competition.
|
ICLR | 2025 | 21 |
| Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields.
|
AISTATS | 2025 | 0 |
| Linearization Turns Neural Operators into Function-Valued Gaussian Processes.
|
ICML | 2025 | 0 |
| Computation-Aware Kalman Filtering and Smoothing.
|
AISTATS | 2025 | 0 |
| Debiasing Mini-Batch Quadratics for Applications in Deep Learning.
|
ICLR | 2025 | 0 |
| Reparameterization invariance in approximate Bayesian inference.
|
NIPS/NeurIPS | 2024 | 15 |
| A Greedy Approximation for k-Determinantal Point Processes.
|
AISTATS | 2024 | 3 |
| Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference.
|
NIPS/NeurIPS | 2024 | 9 |
| FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning.
|
NIPS/NeurIPS | 2024 | 11 |
| Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations.
|
ICML | 2024 | 5 |
| Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI.
|
ICML | 2024 | 62 |
| Parallel-in-Time Probabilistic Numerical ODE Solvers.
|
JMLR | 2024 | 0 |
| Stable Implementation of Probabilistic ODE Solvers.
|
JMLR | 2024 | 0 |
| Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures.
|
NIPS/NeurIPS | 2023 | 36 |
| The Geometry of Neural Nets' Parameter Spaces Under Reparametrization.
|
NIPS/NeurIPS | 2023 | 17 |
| Baysian numerical integration with neural networks.
|
UAI | 2023 | 1 |
| Probabilistic Exponential Integrators.
|
NIPS/NeurIPS | 2023 | 6 |
| The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions.
|
NIPS/NeurIPS | 2023 | 14 |
| Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks.
|
NIPS/NeurIPS | 2022 | 16 |
| Wasserstein t-SNE.
|
ECML/PKDD | 2022 | 3 |
| Fenrir: Physics-Enhanced Regression for Initial Value Problems.
|
ICML | 2022 | 16 |
| Posterior and Computational Uncertainty in Gaussian Processes.
|
NIPS/NeurIPS | 2022 | 22 |
| Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference.
|
AISTATS | 2022 | 3 |
| Probabilistic ODE Solutions in Millions of Dimensions.
|
ICML | 2022 | 0 |
| Preconditioning for Scalable Gaussian Process Hyperparameter Optimization.
|
ICML | 2022 | 0 |
| Fast predictive uncertainty for classification with Bayesian deep networks.
|
UAI | 2022 | 0 |
| Being a Bit Frequentist Improves Bayesian Neural Networks.
|
AISTATS | 2022 | 0 |
| Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations.
|
AISTATS | 2022 | 0 |
| Pick-and-Mix Information Operators for Probabilistic ODE Solvers.
|
AISTATS | 2022 | 0 |
| Bayesian Quadrature on Riemannian Data Manifolds.
|
ICML | 2021 | 4 |
| A Probabilistic State Space Model for Joint Inference from Differential Equations and Data.
|
NIPS/NeurIPS | 2021 | 27 |
| Linear-Time Probabilistic Solution of Boundary Value Problems.
|
NIPS/NeurIPS | 2021 | 8 |
| Laplace Redux - Effortless Bayesian Deep Learning.
|
NIPS/NeurIPS | 2021 | 405 |
| High-Dimensional Gaussian Process Inference with Derivatives.
|
ICML | 2021 | 23 |
| ResNet After All: Neural ODEs and Their Numerical Solution.
|
ICLR | 2021 | 6 |
| Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks.
|
NIPS/NeurIPS | 2021 | 11 |
| Probabilistic DAG search.
|
UAI | 2021 | 4 |
| Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers.
|
ICML | 2021 | 0 |
| Learnable uncertainty under Laplace approximations.
|
UAI | 2021 | 0 |
| Calibrated Adaptive Probabilistic ODE Solvers.
|
AISTATS | 2021 | 0 |
| An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence.
|
NIPS/NeurIPS | 2021 | 0 |
| Robot Learning With Crash Constraints.
|
IEEE Robotics and Automation Letters | 2021 | 0 |
| Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks.
|
ICML | 2020 | 0 |
| Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems.
|
ICML | 2020 | 22 |
| Probabilistic Linear Solvers for Machine Learning.
|
NIPS/NeurIPS | 2020 | 18 |
| Integrals over Gaussians under Linear Domain Constraints.
|
AISTATS | 2020 | 0 |
| Modular Block-diagonal Curvature Approximations for Feedforward Architectures.
|
AISTATS | 2020 | 0 |
| BackPACK: Packing more into Backprop.
|
ICLR | 2020 | 0 |
| Conjugate Gradients for Kernel Machines.
|
JMLR | 2020 | 0 |
| Fast and Robust Shortest Paths on Manifolds Learned from Data.
|
AISTATS | 2019 | 40 |
| Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization.
|
AISTATS | 2019 | 3 |
| Convergence Guarantees for Adaptive Bayesian Quadrature Methods.
|
NIPS/NeurIPS | 2019 | 41 |
| Limitations of the empirical Fisher approximation for natural gradient descent.
|
NIPS/NeurIPS | 2019 | 0 |
| Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients.
|
ICML | 2018 | 0 |
| Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization.
|
ICRA | 2017 | 136 |
| Coupling Adaptive Batch Sizes with Learning Rates.
|
UAI | 2017 | 0 |
| Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets.
|
AISTATS | 2017 | 0 |
| Probabilistic Line Searches for Stochastic Optimization.
|
JMLR | 2017 | 0 |
| Automatic LQR tuning based on Gaussian process global optimization.
|
ICRA | 2016 | 177 |
| Active Uncertainty Calibration in Bayesian ODE Solvers.
|
UAI | 2016 | 48 |
| Probabilistic Approximate Least-Squares.
|
AISTATS | 2016 | 16 |
| Batch Bayesian Optimization via Local Penalization.
|
AISTATS | 2016 | 0 |
| Dual Control for Approximate Bayesian Reinforcement Learning.
|
JMLR | 2016 | 0 |
| Inference of Cause and Effect with Unsupervised Inverse Regression.
|
AISTATS | 2015 | 79 |
| Probabilistic Line Searches for Stochastic Optimization.
|
NIPS/NeurIPS | 2015 | 131 |
| Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature.
|
NIPS/NeurIPS | 2014 | 116 |
| Efficient Bayesian local model learning for control.
|
IROS | 2014 | 17 |
| Incremental Local Gaussian Regression.
|
NIPS/NeurIPS | 2014 | 59 |
| Probabilistic ODE Solvers with Runge-Kutta Means.
|
NIPS/NeurIPS | 2014 | 126 |
| Active Learning of Linear Embeddings for Gaussian Processes.
|
UAI | 2014 | 0 |
| Probabilistic Solutions to Differential Equations and their Application to Riemannian Statistics.
|
AISTATS | 2014 | 0 |
| Fast Probabilistic Optimization from Noisy Gradients.
|
ICML | 2013 | 36 |
| The Randomized Dependence Coefficient.
|
NIPS/NeurIPS | 2013 | 205 |
| Quasi-Newton methods: a new direction.
|
JMLR | 2013 | 0 |
| Quasi-Newton Methods: A New Direction.
|
ICML | 2012 | 108 |
| Learning tracking control with forward models.
|
ICRA | 2012 | 10 |
| Entropy Search for Information-Efficient Global Optimization.
|
JMLR | 2012 | 0 |
| Kernel Topic Models.
|
AISTATS | 2012 | 0 |
| Optimal Reinforcement Learning for Gaussian Systems.
|
NIPS/NeurIPS | 2011 | 18 |
| Coherent Inference on Optimal Play in Game Trees.
|
AISTATS | 2010 | 4 |