Philipp Hennig

227 papers A* 37A 27C 1Journal 141Unranked 19

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Bayesian Scattering: A Principled Baseline for Uncertainty on Image Data. CoRR Bernardo Fichera, Zarko Ivkovic, Kjell Jorner, Philipp Hennig, Viacheslav Borovitskiy
2026	J	`jnl`	Visualizing stability: a sensitivity analysis framework for t-SNE embeddings. Frontiers Bioinform. Susanne Zabel, Philipp Hennig, Kay Nieselt
2025	J	`jnl`	Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition. CoRR Priya Kasimbeg, Frank Schneider, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim, Boyuan Feng, Less Wright, Edward Z. Yang, Zachary Nado, Sourabh Medapati, Philipp Hennig, Michael Rabbat, George E. Dahl
2025	J	`jnl`	Accelerating Non-Conjugate Gaussian Processes By Trading Off Computation For Uncertainty. Trans. Mach. Learn. Res. Lukas Tatzel, Jonathan Wenger, Frank Schneider, Philipp Hennig
2025	A*	`conf`	Accelerating neural network training: An analysis of the AlgoPerf competition. ICLR Priya Kasimbeg, Frank Schneider, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim, Boyuan Feng, Less Wright, Edward Z. Yang, Zachary Nado, Sourabh Medapati, Philipp Hennig, Michael Rabbat, George E. Dahl
2025	J	`jnl`	Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs. Trans. Mach. Learn. Res. Emilia Magnani, Nicholas Krämer, Runa Eschenhagen, Lorenzo Rosasco, Philipp Hennig
2025	J	`jnl`	Assessing the risk of future Dunkelflaute events for Germany using generative deep learning. CoRR Felix Strnad, Jonathan Schmidt, Fabian Mockert, Philipp Hennig, Nicole Ludwig
2025	J	`jnl`	Closed-Form Last Layer Optimization. CoRR Alexandre Galashov, Nathaël Da Costa, Liyuan Xu, Philipp Hennig, Arthur Gretton
2025	A	`conf`	Computation-Aware Kalman Filtering and Smoothing. AISTATS Marvin Pförtner, Jonathan Wenger, Jon Cockayne, Philipp Hennig
2025	J	`jnl`	Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods. CoRR Andres Fernandez, Frank Schneider, Maren Mahsereci, Philipp Hennig
2025	J	`jnl`	Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods. Trans. Mach. Learn. Res. Andres Fernandez, Frank Schneider, Maren Mahsereci, Philipp Hennig
2025	A*	`conf`	Debiasing Mini-Batch Quadratics for Applications in Deep Learning. ICLR Lukas Tatzel, Bálint Mucsányi, Osane Hackel, Philipp Hennig
2025	A	`conf`	Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields. AISTATS Tim Weiland, Marvin Pförtner, Philipp Hennig
2025	J	`jnl`	Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields. CoRR Tim Weiland, Marvin Pförtner, Philipp Hennig
2025	J	`jnl`	Gaussian Processes and Reproducing Kernels: Connections and Equivalences. CoRR Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic, Bharath K. Sriperumbudur
2025	—	`conf`	Geometric Gaussian Approximations of Probability Distributions. GSI (3) Nathaël Da Costa, Bálint Mucsányi, Philipp Hennig
2025	J	`jnl`	Geometric Gaussian Approximations of Probability Distributions. CoRR Nathaël Da Costa, Bálint Mucsányi, Philipp Hennig
2025	J	`jnl`	Learning convolution operators on compact Abelian groups. CoRR Emilia Magnani, Ernesto De Vito, Philipp Hennig, Lorenzo Rosasco
2025	A*	`conf`	Linearization Turns Neural Operators into Function-Valued Gaussian Processes. ICML Emilia Magnani, Marvin Pförtner, Tobias Weber, Philipp Hennig
2025	J	`jnl`	Mitigating Forgetting in Low Rank Adaptation. CoRR Joanna Sliwa, Frank Schneider, Philipp Hennig, José Miguel Hernández-Lobato
2025	—	`ed.`	Proceedings of the First International Conference on Probabilistic Numerics (ProbNum 2025), 1-3 September 2025, EURECOM, Sophia Antipolis, France ProbNum Motonobu Kanagawa, Jon Cockayne, Alexandra Gessner, Philipp Hennig
2025	J	`jnl`	Rethinking Approximate Gaussian Inference in Classification. CoRR Bálint Mucsányi, Nathaël Da Costa, Philipp Hennig
2025	J	`jnl`	Sketching Low-Rank Plus Diagonal Matrices. CoRR Andres Fernandez, Felix Dangel, Philipp Hennig, Frank Schneider
2025	J	`jnl`	laplax - Laplace Approximations with JAX. CoRR Tobias Weber, Bálint Mucsányi, Lenard Rommel, Thomas Christie, Lars Kasüschke, Marvin Pförtner, Philipp Hennig
2024	A	`conf`	A Greedy Approximation for k-Determinantal Point Processes. AISTATS Julia Grosse, Rahel Fischer, Roman Garnett, Philipp Hennig
2024	A*	`conf`	Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference. NeurIPS Jonathan Wenger, Kaiwen Wu, Philipp Hennig, Jacob R. Gardner, Geoff Pleiss, John P. Cunningham
2024	J	`jnl`	Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference. CoRR Jonathan Wenger, Kaiwen Wu, Philipp Hennig, Jacob R. Gardner, Geoff Pleiss, John P. Cunningham
2024	J	`jnl`	Computation-Aware Kalman Filtering and Smoothing. CoRR Marvin Pförtner, Jonathan Wenger, Jon Cockayne, Philipp Hennig
2024	J	`jnl`	Debiasing Mini-Batch Quadratics for Applications in Deep Learning. CoRR Lukas Tatzel, Bálint Mucsányi, Osane Hackel, Philipp Hennig
2024	A*	`conf`	Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations. ICML Jonas Beck, Nathanael Bosch, Michael Deistler, Kyra L. Kadhim, Jakob H. Macke, Philipp Hennig, Philipp Berens
2024	J	`jnl`	Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations. CoRR Jonas Beck, Nathanael Bosch, Michael Deistler, Kyra L. Kadhim, Jakob H. Macke, Philipp Hennig, Philipp Berens
2024	J	`jnl`	Efficient Weight-Space Laplace-Gaussian Filtering and Smoothing for Sequential Deep Learning. CoRR Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig
2024	A*	`conf`	FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning. NeurIPS Tristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler
2024	J	`jnl`	FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning. CoRR Tristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler
2024	J	`jnl`	Flexible inference in heterogeneous and attributed multilayer networks. CoRR Martina Contisciani, Marius Hobbhahn, Eleanor A. Power, Philipp Hennig, Caterina De Bacco
2024	J	`jnl`	Linearization Turns Neural Operators into Function-Valued Gaussian Processes. CoRR Emilia Magnani, Marvin Pförtner, Tobias Weber, Philipp Hennig
2024	J	`jnl`	Parallel-in-Time Probabilistic Numerical ODE Solvers. J. Mach. Learn. Res. Nathanael Bosch, Adrien Corenflos, Fatemeh Yaghoobi, Filip Tronarp, Philipp Hennig, Simo Särkkä
2024	J	`jnl`	Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI. CoRR Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David B. Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, José Miguel Hernández-Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A. Osborne, Tim G. J. Rudner, David Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang
2024	A*	`conf`	Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI. ICML Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David B. Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, José Miguel Hernández-Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A. Osborne, Tim G. J. Rudner, David Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang
2024	J	`jnl`	Probabilistic ODE Solvers for Integration Error-Aware Numerical Optimal Control. CoRR Amon Lahr, Filip Tronarp, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig, Melanie N. Zeilinger
2024	—	`conf`	Probabilistic ODE solvers for integration error-aware numerical optimal control. L4DC Amon Lahr, Filip Tronarp, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig, Melanie N. Zeilinger
2024	A*	`conf`	Reparameterization invariance in approximate Bayesian inference. NeurIPS Hrittik Roy, Marco Miani, Carl Henrik Ek, Philipp Hennig, Marvin Pförtner, Lukas Tatzel, Søren Hauberg
2024	J	`jnl`	Reparameterization invariance in approximate Bayesian inference. CoRR Hrittik Roy, Marco Miani, Carl Henrik Ek, Philipp Hennig, Marvin Pförtner, Lukas Tatzel, Søren Hauberg
2024	J	`jnl`	Scaling up Probabilistic PDE Simulators with Structured Volumetric Information. CoRR Tim Weiland, Marvin Pförtner, Philipp Hennig
2024	J	`jnl`	Spatiotemporally Coherent Probabilistic Generation of Weather from Climate. CoRR Jonathan Schmidt, Luca Schmidt, Felix Strnad, Nicole Ludwig, Philipp Hennig
2024	J	`jnl`	Stable Implementation of Probabilistic ODE Solvers. J. Mach. Learn. Res. Nicholas Krämer, Philipp Hennig
2024	J	`jnl`	Uncertainty-Guided Optimization on Large Language Model Search Trees. CoRR Julia Grosse, Ruotian Wu, Ahmad Rashid, Philipp Hennig, Pascal Poupart, Agustinus Kristiadi
2024	J	`jnl`	VIPurPCA: Visualizing and Propagating Uncertainty in Principal Component Analysis. IEEE Trans. Vis. Comput. Graph. Susanne Zabel, Philipp Hennig, Kay Nieselt
2023	J	`jnl`	Accelerating Generalized Linear Models by Trading off Computation for Uncertainty. CoRR Lukas Tatzel, Jonathan Wenger, Frank Schneider, Philipp Hennig
2023	J	`jnl`	Bayesian Numerical Integration with Neural Networks. CoRR Katharina Ott, Michael Tiemann, Philipp Hennig, François-Xavier Briol
2023	A	`conf`	Baysian numerical integration with neural networks. UAI Katharina Ott, Michael Tiemann, Philipp Hennig, François-Xavier Briol
2023	J	`jnl`	Benchmarking Neural Network Training Algorithms. CoRR George E. Dahl, Frank Schneider, Zachary Nado, Naman Agarwal, Chandramouli Shama Sastry, Philipp Hennig, Sourabh Medapati, Runa Eschenhagen, Priya Kasimbeg, Daniel Suo, Juhan Bae, Justin Gilmer, Abel L. Peirson, Bilal Khan, Rohan Anil, Mike Rabbat, Shankar Krishnan, Daniel Snider, Ehsan Amid, Kongtao Chen, Chris J. Maddison, Rakshith Vasudev, Michal Badura, Ankush Garg, Peter Mattson
2023	A*	`conf`	Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures. NeurIPS Runa Eschenhagen, Alexander Immer, Richard E. Turner, Frank Schneider, Philipp Hennig
2023	J	`jnl`	Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures. CoRR Runa Eschenhagen, Alexander Immer, Richard E. Turner, Frank Schneider, Philipp Hennig
2023	J	`jnl`	Optimistic Optimization of Gaussian Process Samples. Trans. Mach. Learn. Res. Julia Grosse, Cheng Zhang, Philipp Hennig
2023	J	`jnl`	Parallel-in-Time Probabilistic Numerical ODE Solvers. CoRR Nathanael Bosch, Adrien Corenflos, Fatemeh Yaghoobi, Filip Tronarp, Philipp Hennig, Simo Särkkä
2023	A*	`conf`	Probabilistic Exponential Integrators. NeurIPS Nathanael Bosch, Philipp Hennig, Filip Tronarp
2023	J	`jnl`	Probabilistic Exponential Integrators. CoRR Nathanael Bosch, Philipp Hennig, Filip Tronarp
2023	J	`jnl`	Sample Path Regularity of Gaussian Processes from the Covariance Kernel. CoRR Nathaël Da Costa, Marvin Pförtner, Lancelot Da Costa, Philipp Hennig
2023	A*	`conf`	The Geometry of Neural Nets' Parameter Spaces Under Reparametrization. NeurIPS Agustinus Kristiadi, Felix Dangel, Philipp Hennig
2023	J	`jnl`	The Geometry of Neural Nets' Parameter Spaces Under Reparametrization. CoRR Agustinus Kristiadi, Felix Dangel, Philipp Hennig
2023	A*	`conf`	The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions. NeurIPS Jonathan Schmidt, Philipp Hennig, Jörg Nick, Filip Tronarp
2023	J	`jnl`	The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions. CoRR Jonathan Schmidt, Philipp Hennig, Jörg Nick, Filip Tronarp
2023	J	`jnl`	Uncertainty and Structure in Neural Ordinary Differential Equations. CoRR Katharina Ott, Michael Tiemann, Philipp Hennig
2023	J	`jnl`	ViViT: Curvature Access Through The Generalized Gauss-Newton's Low-Rank Structure. Trans. Mach. Learn. Res. Felix Dangel, Lukas Tatzel, Philipp Hennig
2022	J	`jnl`	Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs. CoRR Emilia Magnani, Nicholas Krämer, Runa Eschenhagen, Lorenzo Rosasco, Philipp Hennig
2022	A	`conf`	Being a Bit Frequentist Improves Bayesian Neural Networks. AISTATS Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2022	J	`jnl`	Correction to: Probabilistic solvers enable a straight-forward exploration of numerical uncertainty in neuroscience models. J. Comput. Neurosci. Jonathan Oesterle, Nicholas Krämer, Philipp Hennig, Philipp Berens
2022	A	`conf`	Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference. AISTATS Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike von Luxburg
2022	J	`jnl`	Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference. CoRR Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike von Luxburg
2022	A	`conf`	Fast predictive uncertainty for classification with Bayesian deep networks. UAI Marius Hobbhahn, Agustinus Kristiadi, Philipp Hennig
2022	A*	`conf`	Fenrir: Physics-Enhanced Regression for Initial Value Problems. ICML Filip Tronarp, Nathanael Bosch, Philipp Hennig
2022	J	`jnl`	Fenrir: Physics-Enhanced Regression for Initial Value Problems. CoRR Filip Tronarp, Nathanael Bosch, Philipp Hennig
2022	J	`jnl`	Optimistic Optimization of Gaussian Process Samples. CoRR Julia Grosse, Cheng Zhang, Philipp Hennig
2022	J	`jnl`	Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers. CoRR Marvin Pförtner, Ingo Steinwart, Philipp Hennig, Jonathan Wenger
2022	A	`conf`	Pick-and-Mix Information Operators for Probabilistic ODE Solvers. AISTATS Nathanael Bosch, Filip Tronarp, Philipp Hennig
2022	A*	`conf`	Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks. NeurIPS Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig
2022	J	`jnl`	Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks. CoRR Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig
2022	A*	`conf`	Posterior and Computational Uncertainty in Gaussian Processes. NeurIPS Jonathan Wenger, Geoff Pleiss, Marvin Pförtner, Philipp Hennig, John P. Cunningham
2022	J	`jnl`	Posterior and Computational Uncertainty in Gaussian Processes. CoRR Jonathan Wenger, Geoff Pleiss, Marvin Pförtner, Philipp Hennig, John P. Cunningham
2022	A*	`conf`	Preconditioning for Scalable Gaussian Process Hyperparameter Optimization. ICML Jonathan Wenger, Geoff Pleiss, Philipp Hennig, John P. Cunningham, Jacob R. Gardner
2022	A	`conf`	Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations. AISTATS Nicholas Krämer, Jonathan Schmidt, Philipp Hennig
2022	A*	`conf`	Probabilistic ODE Solutions in Millions of Dimensions. ICML Nicholas Krämer, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig
2022	J	`jnl`	Probabilistic solvers enable a straight-forward exploration of numerical uncertainty in neuroscience models. J. Comput. Neurosci. Jonathan Oesterle, Nicholas Krämer, Philipp Hennig, Philipp Berens
2022	—	`conf`	Uncertainty in equation learning. GECCO Companion Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius
2022	—	`conf`	Wasserstein t-SNE. ECML/PKDD (1) Fynn Bachmann, Philipp Hennig, Dmitry Kobak
2022	J	`jnl`	Wasserstein t-SNE. CoRR Fynn Bachmann, Philipp Hennig, Dmitry Kobak
2021	A*	`conf`	A Probabilistic State Space Model for Joint Inference from Differential Equations and Data. NeurIPS Jonathan Schmidt, Nicholas Krämer, Philipp Hennig
2021	J	`jnl`	A Probabilistic State Space Model for Joint Inference from Differential Equations and Data. CoRR Jonathan Schmidt, Nicholas Krämer, Philipp Hennig
2021	J	`jnl`	A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization. CoRR Filip de Roos, Carl Jidling, Adrian Wills, Thomas B. Schön, Philipp Hennig
2021	A*	`conf`	An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence. NeurIPS Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2021	J	`jnl`	Bayesian ODE solvers: the maximum a posteriori estimate. Stat. Comput. Filip Tronarp, Simo Särkkä, Philipp Hennig
2021	A*	`conf`	Bayesian Quadrature on Riemannian Data Manifolds. ICML Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis
2021	J	`jnl`	Bayesian Quadrature on Riemannian Data Manifolds. CoRR Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis
2021	J	`jnl`	Being a Bit Frequentist Improves Bayesian Neural Networks. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2021	A	`conf`	Calibrated Adaptive Probabilistic ODE Solvers. AISTATS Nathanael Bosch, Philipp Hennig, Filip Tronarp
2021	J	`jnl`	Cockpit: A Practical Debugging Tool for Training Deep Neural Networks. CoRR Frank Schneider, Felix Dangel, Philipp Hennig
2021	A*	`conf`	Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks. NeurIPS Frank Schneider, Felix Dangel, Philipp Hennig
2021	A*	`conf`	Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers. ICML Robin M. Schmidt, Frank Schneider, Philipp Hennig
2021	A*	`conf`	High-Dimensional Gaussian Process Inference with Derivatives. ICML Filip de Roos, Alexandra Gessner, Philipp Hennig
2021	J	`jnl`	High-Dimensional Gaussian Process Inference with Derivatives. CoRR Filip de Roos, Alexandra Gessner, Philipp Hennig
2021	J	`jnl`	Informed Equation Learning. CoRR Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius
2021	J	`jnl`	Laplace Matching for fast Approximate Inference in Generalized Linear Models. CoRR Marius Hobbhahn, Philipp Hennig
2021	A*	`conf`	Laplace Redux - Effortless Bayesian Deep Learning. NeurIPS Erik A. Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig
2021	J	`jnl`	Laplace Redux - Effortless Bayesian Deep Learning. CoRR Erik A. Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig
2021	A	`conf`	Learnable uncertainty under Laplace approximations. UAI Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2021	A*	`conf`	Linear-Time Probabilistic Solution of Boundary Value Problems. NeurIPS Nicholas Krämer, Philipp Hennig
2021	J	`jnl`	Linear-Time Probabilistic Solutions of Boundary Value Problems. CoRR Nicholas Krämer, Philipp Hennig
2021	J	`jnl`	Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning. CoRR Runa Eschenhagen, Erik A. Daxberger, Philipp Hennig, Agustinus Kristiadi
2021	J	`jnl`	Pick-and-Mix Information Operators for Probabilistic ODE Solvers. CoRR Nathanael Bosch, Filip Tronarp, Philipp Hennig
2021	J	`jnl`	ProbNum: Probabilistic Numerics in Python. CoRR Jonathan Wenger, Nicholas Krämer, Marvin Pförtner, Jonathan Schmidt, Nathanael Bosch, Nina Effenberger, Johannes Zenn, Alexandra Gessner, Toni Karvonen, François-Xavier Briol, Maren Mahsereci, Philipp Hennig
2021	J	`jnl`	Probabilistic DAG Search. CoRR Julia Grosse, Cheng Zhang, Philipp Hennig
2021	A	`conf`	Probabilistic DAG search. UAI Julia Grosse, Cheng Zhang, Philipp Hennig
2021	J	`jnl`	Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations. CoRR Nicholas Krämer, Jonathan Schmidt, Philipp Hennig
2021	J	`jnl`	Probabilistic Numerical Methods - From Theory to Implementation (Dagstuhl Seminar 21432). Dagstuhl Reports Philipp Hennig, Ilse C. F. Ipsen, Maren Mahsereci, Tim Sullivan
2021	J	`jnl`	Probabilistic ODE Solutions in Millions of Dimensions. CoRR Nicholas Krämer, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig
2021	J	`jnl`	Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning. CoRR Jonathan Wenger, Geoff Pleiss, Philipp Hennig, John P. Cunningham, Jacob R. Gardner
2021	A*	`conf`	ResNet After All: Neural ODEs and Their Numerical Solution. ICLR Katharina Ott, Prateek Katiyar, Philipp Hennig, Michael Tiemann
2021	J	`jnl`	Robot Learning With Crash Constraints. IEEE Robotics Autom. Lett. Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe
2021	J	`jnl`	ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure. CoRR Felix Dangel, Lukas Tatzel, Philipp Hennig
2020	A*	`conf`	BackPACK: Packing more into Backprop. ICLR Felix Dangel, Frederik Kunstner, Philipp Hennig
2020	J	`jnl`	Bayesian ODE Solvers: The Maximum A Posteriori Estimate. CoRR Filip Tronarp, Simo Särkkä, Philipp Hennig
2020	A*	`conf`	Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. ICML Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	J	`jnl`	Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	J	`jnl`	Calibrated Adaptive Probabilistic ODE Solvers. CoRR Nathanael Bosch, Philipp Hennig, Filip Tronarp
2020	J	`jnl`	Conjugate Gradients for Kernel Machines. J. Mach. Learn. Res. Simon Bartels, Philipp Hennig
2020	J	`jnl`	Convergence rates of Gaussian ODE filters. Stat. Comput. Hans Kersting, Timothy John Sullivan, Philipp Hennig
2020	J	`jnl`	Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers. CoRR Robin M. Schmidt, Frank Schneider, Philipp Hennig
2020	A*	`conf`	Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems. ICML Hans Kersting, Nicholas Krämer, Martin Schiegg, Christian Daniel, Michael Tiemann, Philipp Hennig
2020	J	`jnl`	Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems. CoRR Hans Kersting, Nicholas Krämer, Martin Schiegg, Christian Daniel, Michael Tiemann, Philipp Hennig
2020	J	`jnl`	Fast Predictive Uncertainty for Classification with Bayesian Deep Networks. CoRR Marius Hobbhahn, Agustinus Kristiadi, Philipp Hennig
2020	J	`jnl`	Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	A	`conf`	Integrals over Gaussians under Linear Domain Constraints. AISTATS Alexandra Gessner, Oindrila Kanjilal, Philipp Hennig
2020	J	`jnl`	Learnable Uncertainty under Laplace Approximations. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	A	`conf`	Modular Block-diagonal Curvature Approximations for Feedforward Architectures. AISTATS Felix Dangel, Stefan Harmeling, Philipp Hennig
2020	A*	`conf`	Probabilistic Linear Solvers for Machine Learning. NeurIPS Jonathan Wenger, Philipp Hennig
2020	J	`jnl`	Probabilistic Linear Solvers for Machine Learning. CoRR Jonathan Wenger, Philipp Hennig
2020	J	`jnl`	Robot Learning with Crash Constraints. CoRR Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe
2020	—	`conf`	Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering. ICBINB@NeurIPS Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig
2020	J	`jnl`	Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering. CoRR Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig
2020	J	`jnl`	Stable Implementation of Probabilistic ODE Solvers. CoRR Nicholas Krämer, Philipp Hennig
2020	J	`jnl`	When are Neural ODE Solutions Proper ODEs? CoRR Katharina Ott, Prateek Katiyar, Philipp Hennig, Michael Tiemann
2019	J	`jnl`	A Modular Approach to Block-diagonal Hessian Approximations for Second-order Optimization Methods. CoRR Felix Dangel, Philipp Hennig
2019	J	`jnl`	A probabilistic model for the numerical solution of initial value problems. Stat. Comput. Michael Schober, Simo Särkkä, Philipp Hennig
2019	A	`conf`	Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization. AISTATS Filip de Roos, Philipp Hennig
2019	J	`jnl`	Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization. CoRR Filip de Roos, Philipp Hennig
2019	J	`jnl`	BackPACK: Packing more into backprop. CoRR Felix Dangel, Frederik Kunstner, Philipp Hennig
2019	J	`jnl`	Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties. CoRR Alonso Marco, Dominik Baumann, Philipp Hennig, Sebastian Trimpe
2019	J	`jnl`	Conjugate Gradients for Kernel Machines. CoRR Simon Bartels, Philipp Hennig
2019	A*	`conf`	Convergence Guarantees for Adaptive Bayesian Quadrature Methods. NeurIPS Motonobu Kanagawa, Philipp Hennig
2019	J	`jnl`	Convergence Guarantees for Adaptive Bayesian Quadrature Methods. CoRR Motonobu Kanagawa, Philipp Hennig
2019	—	`conf`	DeepOBS: A Deep Learning Optimizer Benchmark Suite. ICLR (Poster) Frank Schneider, Lukas Balles, Philipp Hennig
2019	J	`jnl`	DeepOBS: A Deep Learning Optimizer Benchmark Suite. CoRR Frank Schneider, Lukas Balles, Philipp Hennig
2019	A	`conf`	Fast and Robust Shortest Paths on Manifolds Learned from Data. AISTATS Georgios Arvanitidis, Søren Hauberg, Philipp Hennig, Michael Schober
2019	J	`jnl`	Fast and Robust Shortest Paths on Manifolds Learned from Data. CoRR Georgios Arvanitidis, Søren Hauberg, Philipp Hennig, Michael Schober
2019	J	`jnl`	Integrals over Gaussians under Linear Domain Constraints. CoRR Alexandra Gessner, Oindrila Kanjilal, Philipp Hennig
2019	J	`jnl`	Limitations of the Empirical Fisher Approximation. CoRR Frederik Kunstner, Lukas Balles, Philipp Hennig
2019	A*	`conf`	Limitations of the empirical Fisher approximation for natural gradient descent. NeurIPS Frederik Kunstner, Philipp Hennig, Lukas Balles
2019	J	`jnl`	Probabilistic linear solvers: a unifying view. Stat. Comput. Simon Bartels, Jon Cockayne, Ilse C. F. Ipsen, Philipp Hennig
2019	J	`jnl`	Probabilistic solutions to ordinary differential equations as nonlinear Bayesian filtering: a new perspective. Stat. Comput. Filip Tronarp, Hans Kersting, Simo Särkkä, Philipp Hennig
2019	J	`jnl`	Uncertainty Estimates for Ordinal Embeddings. CoRR Michael Lohaus, Philipp Hennig, Ulrike von Luxburg
2018	J	`jnl`	Convergence Rates of Gaussian ODE Filters. CoRR Hans Kersting, Timothy John Sullivan, Philipp Hennig
2018	A*	`conf`	Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients. ICML Lukas Balles, Philipp Hennig
2018	J	`jnl`	Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences. CoRR Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic, Bharath K. Sriperumbudur
2017	J	`jnl`	Bayesian Filtering for ODEs with Bounded Derivatives. CoRR Emilia Magnani, Hans Kersting, Michael Schober, Philipp Hennig
2017	A	`conf`	Coupling Adaptive Batch Sizes with Learning Rates. UAI Lukas Balles, Javier Romero, Philipp Hennig
2017	J	`jnl`	Early Stopping without a Validation Set. CoRR Maren Mahsereci, Lukas Balles, Christoph Lassner, Philipp Hennig
2017	A	`conf`	Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets. AISTATS Aaron Klein, Stefan Falkner, Simon Bartels, Philipp Hennig, Frank Hutter
2017	J	`jnl`	Follow the Signs for Robust Stochastic Optimization. CoRR Lukas Balles, Philipp Hennig
2017	J	`jnl`	Krylov Subspace Recycling for Fast Iterative Least-Squares in Machine Learning. CoRR Filip de Roos, Philipp Hennig
2017	J	`jnl`	On the Design of LQR Kernels for Efficient Controller Learning. CoRR Alonso Marco, Philipp Hennig, Stefan Schaal, Sebastian Trimpe
2017	—	`conf`	On the design of LQR kernels for efficient controller learning. CDC Alonso Marco, Philipp Hennig, Stefan Schaal, Sebastian Trimpe
2017	J	`jnl`	Probabilistic Active Learning of Functions in Structural Causal Models. CoRR Paul K. Rubenstein, Ilya O. Tolstikhin, Philipp Hennig, Bernhard Schölkopf
2017	J	`jnl`	Probabilistic Line Searches for Stochastic Optimization. CoRR Maren Mahsereci, Philipp Hennig
2017	J	`jnl`	Probabilistic Line Searches for Stochastic Optimization. J. Mach. Learn. Res. Maren Mahsereci, Philipp Hennig
2017	J	`jnl`	Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization. CoRR Alonso Marco, Felix Berkenkamp, Philipp Hennig, Angela P. Schoellig, Andreas Krause, Stefan Schaal, Sebastian Trimpe
2017	A*	`conf`	Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization. ICRA Alonso Marco, Felix Berkenkamp, Philipp Hennig, Angela P. Schoellig, Andreas Krause, Stefan Schaal, Sebastian Trimpe
2016	J	`jnl`	A probabilistic model for the numerical solution of initial value problems. CoRR Michael Schober, Simo Särkkä, Philipp Hennig
2016	A	`conf`	Active Uncertainty Calibration in Bayesian ODE Solvers. UAI Hans Kersting, Philipp Hennig
2016	J	`jnl`	Active Uncertainty Calibration in Bayesian ODE Solvers. CoRR Hans Kersting, Philipp Hennig
2016	—	`conf`	Approximate dual control maintaining the value of information with an application to building control. ECC Edgar D. Klenske, Philipp Hennig, Bernhard Schölkopf, Melanie Nicole Zeilinger
2016	J	`jnl`	Automatic LQR Tuning Based on Gaussian Process Global Optimization. CoRR Alonso Marco, Philipp Hennig, Jeannette Bohg, Stefan Schaal, Sebastian Trimpe
2016	A*	`conf`	Automatic LQR tuning based on Gaussian process global optimization. ICRA Alonso Marco, Philipp Hennig, Jeannette Bohg, Stefan Schaal, Sebastian Trimpe
2016	A	`conf`	Batch Bayesian Optimization via Local Penalization. AISTATS Javier González, Zhenwen Dai, Philipp Hennig, Neil D. Lawrence
2016	J	`jnl`	Coupling Adaptive Batch Sizes with Learning Rates. CoRR Lukas Balles, Javier Romero, Philipp Hennig
2016	J	`jnl`	Dual Control for Approximate Bayesian Reinforcement Learning. J. Mach. Learn. Res. Edgar D. Klenske, Philipp Hennig
2016	J	`jnl`	Exact Sampling from Determinantal Point Processes. CoRR Philipp Hennig, Roman Garnett
2016	J	`jnl`	Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets. CoRR Aaron Klein, Stefan Falkner, Simon Bartels, Philipp Hennig, Frank Hutter
2016	J	`jnl`	Gaussian Process-Based Predictive Control for Periodic Error Correction. IEEE Trans. Control. Syst. Technol. Edgar D. Klenske, Melanie Nicole Zeilinger, Bernhard Schölkopf, Philipp Hennig
2016	J	`jnl`	New Directions for Learning with Kernels and Gaussian Processes (Dagstuhl Seminar 16481). Dagstuhl Reports Arthur Gretton, Philipp Hennig, Carl Edward Rasmussen, Bernhard Schölkopf
2016	A	`conf`	Probabilistic Approximate Least-Squares. AISTATS Simon Bartels, Philipp Hennig
2015	—	`conf`	A Random Riemannian Metric for Probabilistic Shortest-Path Tractography. MICCAI (1) Søren Hauberg, Michael Schober, Matthew G. Liptrot, Philipp Hennig, Aasa Feragen
2015	J	`jnl`	Dual Control for Approximate Bayesian Reinforcement Learning. CoRR Edgar D. Klenske, Philipp Hennig
2015	A	`conf`	Inference of Cause and Effect with Unsupervised Inverse Regression. AISTATS Eleni Sgouritsa, Dominik Janzing, Philipp Hennig, Bernhard Schölkopf
2015	J	`jnl`	Probabilistic Interpretation of Linear Solvers. SIAM J. Optim. Philipp Hennig
2015	—	`conf`	Probabilistic Line Searches for Stochastic Optimization. NIPS Maren Mahsereci, Philipp Hennig
2015	J	`jnl`	Probabilistic Line Searches for Stochastic Optimization. CoRR Maren Mahsereci, Philipp Hennig
2015	J	`jnl`	Probabilistic Numerics and Uncertainty in Computations. CoRR Philipp Hennig, Michael A. Osborne, Mark A. Girolami
2014	A	`conf`	Active Learning of Linear Embeddings for Gaussian Processes. UAI Roman Garnett, Michael A. Osborne, Philipp Hennig
2014	A	`conf`	Efficient Bayesian local model learning for control. IROS Franziska Meier, Philipp Hennig, Stefan Schaal
2014	—	`conf`	Incremental Local Gaussian Regression. NIPS Franziska Meier, Philipp Hennig, Stefan Schaal
2014	J	`jnl`	Local Gaussian Regression. CoRR Franziska Meier, Philipp Hennig, Stefan Schaal
2014	J	`jnl`	Probabilistic Interpretation of Linear Solvers. CoRR Philipp Hennig
2014	—	`conf`	Probabilistic ODE Solvers with Runge-Kutta Means. NIPS Michael Schober, David Duvenaud, Philipp Hennig
2014	J	`jnl`	Probabilistic ODE Solvers with Runge-Kutta Means. CoRR Michael Schober, David Duvenaud, Philipp Hennig
2014	—	`conf`	Probabilistic Progress Bars. GCPR Martin Kiefel, Christian J. Schuler, Philipp Hennig
2014	—	`conf`	Probabilistic Shortest Path Tractography in DTI Using Gaussian Process ODE Solvers. MICCAI (3) Michael Schober, Niklas Kasenburg, Aasa Feragen, Philipp Hennig, Søren Hauberg
2014	A	`conf`	Probabilistic Solutions to Differential Equations and their Application to Riemannian Statistics. AISTATS Philipp Hennig, Søren Hauberg
2014	—	`conf`	Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature. NIPS Tom Gunter, Michael A. Osborne, Roman Garnett, Philipp Hennig, Stephen J. Roberts
2013	J	`jnl`	Active Learning of Linear Embeddings for Gaussian Processes. CoRR Roman Garnett, Michael A. Osborne, Philipp Hennig
2013	—	`conf`	Fast Probabilistic Optimization from Noisy Gradients. ICML (1) Philipp Hennig
2013	—	`conf`	Nonparametric dynamics estimation for time periodic systems. Allerton Edgar D. Klenske, Melanie Nicole Zeilinger, Bernhard Schölkopf, Philipp Hennig
2013	J	`jnl`	Probabilistic Numerical Analysis in Riemannian Statistics. CoRR Philipp Hennig, Søren Hauberg
2013	J	`jnl`	Quasi-Newton methods: a new direction. J. Mach. Learn. Res. Philipp Hennig, Martin Kiefel
2013	—	`conf`	The Randomized Dependence Coefficient. NIPS David López-Paz, Philipp Hennig, Bernhard Schölkopf
2012	J	`jnl`	Entropy Search for Information-Efficient Global Optimization. J. Mach. Learn. Res. Philipp Hennig, Christian J. Schuler
2012	A	`conf`	Kernel Topic Models. AISTATS Philipp Hennig, David H. Stern, Ralf Herbrich, Thore Graepel
2012	A*	`conf`	Learning tracking control with forward models. ICRA Botond Bocsi, Philipp Hennig, Lehel Csató, Jan Peters
2012	J	`jnl`	Quasi-Newton Methods: A New Direction CoRR Philipp Hennig, Martin Kiefel
2012	A*	`conf`	Quasi-Newton Methods: A New Direction. ICML Philipp Hennig, Martin Kiefel
2011	—	`—`	Approximate inference in graphical models. Philipp Hennig
2011	J	`jnl`	Entropy Search for Information-Efficient Global Optimization CoRR Philipp Hennig, Christian J. Schuler
2011	J	`jnl`	Kernel Topic Models CoRR Philipp Hennig, David H. Stern, Ralf Herbrich, Thore Graepel
2011	J	`jnl`	Optimal Reinforcement Learning for Gaussian Systems CoRR Philipp Hennig
2011	—	`conf`	Optimal Reinforcement Learning for Gaussian Systems. NIPS Philipp Hennig
2010	A	`conf`	Coherent Inference on Optimal Play in Game Trees. AISTATS Philipp Hennig, David H. Stern, Thore Graepel
2010	C	`conf`	Using an Infinite Von Mises-Fisher Mixture Model to Cluster Treatment Beam Directions in External Radiation Therapy. ICMLA Mark Bangert, Philipp Hennig, Uwe Oelfke