default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDPhilipp Hennig
Person information
- affiliation: University of Tübingen, Department of Computer Science, Germany
- affiliation: Max Planck Institute for Intelligent Systems, Tübingen, Germany
- affiliation (PhD 2011): University of Cambridge, UK
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j20]Nicholas Krämer, Philipp Hennig:
Stable Implementation of Probabilistic ODE Solvers. J. Mach. Learn. Res. 25: 111:1-111:29 (2024)- [j19]Nathanael Bosch, Adrien Corenflos, Fatemeh Yaghoobi, Filip Tronarp, Philipp Hennig, Simo Särkkä:
Parallel-in-Time Probabilistic Numerical ODE Solvers. J. Mach. Learn. Res. 25: 206:1-206:27 (2024) - [j18]Susanne Zabel
, Philipp Hennig, Kay Nieselt:
VIPurPCA: Visualizing and Propagating Uncertainty in Principal Component Analysis. IEEE Trans. Vis. Comput. Graph. 30(4): 2011-2022 (2024) - [c75]Julia Grosse, Rahel Fischer, Roman Garnett, Philipp Hennig:
A Greedy Approximation for k-Determinantal Point Processes. AISTATS 2024: 3052-3060 - [c74]Jonas Beck, Nathanael Bosch, Michael Deistler, Kyra L. Kadhim, Jakob H. Macke, Philipp Hennig, Philipp Berens:
Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations. ICML 2024 - [c73]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:
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI. ICML 2024 - [c72]Amon Lahr, Filip Tronarp, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig, Melanie N. Zeilinger:
Probabilistic ODE solvers for integration error-aware numerical optimal control. L4DC 2024: 1018-1032 - [i102]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:
Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI. CoRR abs/2402.00809 (2024) - [i101]Jonas Beck, Nathanael Bosch, Michael Deistler, Kyra L. Kadhim, Jakob H. Macke, Philipp Hennig, Philipp Berens:
Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations. CoRR abs/2402.12231 (2024) - [i100]Marvin Pförtner, Jonathan Wenger, Jon Cockayne, Philipp Hennig:
Computation-Aware Kalman Filtering and Smoothing. CoRR abs/2405.08971 (2024) - [i99]Martina Contisciani, Marius Hobbhahn, Eleanor A. Power, Philipp Hennig, Caterina De Bacco:
Flexible inference in heterogeneous and attributed multilayer networks. CoRR abs/2405.20918 (2024) - [i98]Hrittik Roy, Marco Miani, Carl Henrik Ek, Philipp Hennig, Marvin Pförtner, Lukas Tatzel, Søren Hauberg:
Reparameterization invariance in approximate Bayesian inference. CoRR abs/2406.03334 (2024) - [i97]Tim Weiland, Marvin Pförtner, Philipp Hennig:
Scaling up Probabilistic PDE Simulators with Structured Volumetric Information. CoRR abs/2406.05020 (2024) - [i96]Emilia Magnani, Marvin Pförtner, Tobias Weber, Philipp Hennig:
Linearization Turns Neural Operators into Function-Valued Gaussian Processes. CoRR abs/2406.05072 (2024) - [i95]Julia Grosse, Ruotian Wu, Ahmad Rashid, Philipp Hennig, Pascal Poupart, Agustinus Kristiadi:
Uncertainty-Guided Optimization on Large Language Model Search Trees. CoRR abs/2407.03951 (2024) - [i94]Tristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler:
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning. CoRR abs/2407.13711 (2024) - [i93]Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig:
Efficient Weight-Space Laplace-Gaussian Filtering and Smoothing for Sequential Deep Learning. CoRR abs/2410.06800 (2024) - [i92]Lukas Tatzel, Bálint Mucsányi, Osane Hackel, Philipp Hennig:
Debiasing Mini-Batch Quadratics for Applications in Deep Learning. CoRR abs/2410.14325 (2024) - [i91]Jonathan Wenger, Kaiwen Wu, Philipp Hennig, Jacob R. Gardner, Geoff Pleiss, John P. Cunningham:
Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference. CoRR abs/2411.01036 (2024) - 2023
- [j17]Felix Dangel, Lukas Tatzel, Philipp Hennig:
ViViT: Curvature Access Through The Generalized Gauss-Newton's Low-Rank Structure. Trans. Mach. Learn. Res. 2023 (2023) - [j16]Julia Grosse, Cheng Zhang, Philipp Hennig:
Optimistic Optimization of Gaussian Process Samples. Trans. Mach. Learn. Res. 2023 (2023) - [c71]Nathanael Bosch, Philipp Hennig, Filip Tronarp:
Probabilistic Exponential Integrators. NeurIPS 2023 - [c70]Runa Eschenhagen, Alexander Immer, Richard E. Turner, Frank Schneider, Philipp Hennig:
Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures. NeurIPS 2023 - [c69]Agustinus Kristiadi, Felix Dangel, Philipp Hennig:
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization. NeurIPS 2023 - [c68]Jonathan Schmidt, Philipp Hennig, Jörg Nick, Filip Tronarp:
The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions. NeurIPS 2023 - [c67]Katharina Ott, Michael Tiemann, Philipp Hennig, François-Xavier Briol:
Baysian numerical integration with neural networks. UAI 2023: 1606-1617 - [i90]Agustinus Kristiadi, Felix Dangel, Philipp Hennig:
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization. CoRR abs/2302.07384 (2023) - [i89]Katharina Ott, Michael Tiemann, Philipp Hennig, François-Xavier Briol:
Bayesian Numerical Integration with Neural Networks. CoRR abs/2305.13248 (2023) - [i88]Katharina Ott, Michael Tiemann, Philipp Hennig:
Uncertainty and Structure in Neural Ordinary Differential Equations. CoRR abs/2305.13290 (2023) - [i87]Nathanael Bosch, Philipp Hennig, Filip Tronarp:
Probabilistic Exponential Integrators. CoRR abs/2305.14978 (2023) - [i86]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:
Benchmarking Neural Network Training Algorithms. CoRR abs/2306.07179 (2023) - [i85]Jonathan Schmidt, Philipp Hennig, Jörg Nick, Filip Tronarp:
The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions. CoRR abs/2306.07774 (2023) - [i84]Nathanael Bosch, Adrien Corenflos, Fatemeh Yaghoobi, Filip Tronarp, Philipp Hennig, Simo Särkkä:
Parallel-in-Time Probabilistic Numerical ODE Solvers. CoRR abs/2310.01145 (2023) - [i83]Lukas Tatzel, Jonathan Wenger, Frank Schneider, Philipp Hennig:
Accelerating Generalized Linear Models by Trading off Computation for Uncertainty. CoRR abs/2310.20285 (2023) - [i82]Runa Eschenhagen, Alexander Immer, Richard E. Turner, Frank Schneider, Philipp Hennig:
Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures. CoRR abs/2311.00636 (2023) - [i81]Nathaël Da Costa, Marvin Pförtner, Lancelot Da Costa, Philipp Hennig:
Sample Path Regularity of Gaussian Processes from the Covariance Kernel. CoRR abs/2312.14886 (2023) - 2022
- [j15]Jonathan Oesterle, Nicholas Krämer, Philipp Hennig, Philipp Berens:
Probabilistic solvers enable a straight-forward exploration of numerical uncertainty in neuroscience models. J. Comput. Neurosci. 50(4): 485-503 (2022) - [j14]Jonathan Oesterle, Nicholas Krämer, Philipp Hennig, Philipp Berens:
Correction to: Probabilistic solvers enable a straight-forward exploration of numerical uncertainty in neuroscience models. J. Comput. Neurosci. 51(3): 405 (2022) - [c66]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being a Bit Frequentist Improves Bayesian Neural Networks. AISTATS 2022: 529-545 - [c65]Nicholas Krämer, Jonathan Schmidt, Philipp Hennig:
Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations. AISTATS 2022: 625-639 - [c64]Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike von Luxburg:
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference. AISTATS 2022: 1503-1526 - [c63]Nathanael Bosch, Filip Tronarp, Philipp Hennig:
Pick-and-Mix Information Operators for Probabilistic ODE Solvers. AISTATS 2022: 10015-10027 - [c62]Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius:
Uncertainty in equation learning. GECCO Companion 2022: 2298-2305 - [c61]Nicholas Krämer, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig:
Probabilistic ODE Solutions in Millions of Dimensions. ICML 2022: 11634-11649 - [c60]Filip Tronarp, Nathanael Bosch, Philipp Hennig:
Fenrir: Physics-Enhanced Regression for Initial Value Problems. ICML 2022: 21776-21794 - [c59]Jonathan Wenger, Geoff Pleiss, Philipp Hennig, John P. Cunningham, Jacob R. Gardner:
Preconditioning for Scalable Gaussian Process Hyperparameter Optimization. ICML 2022: 23751-23780 - [c58]Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig:
Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks. NeurIPS 2022 - [c57]Jonathan Wenger, Geoff Pleiss, Marvin Pförtner, Philipp Hennig, John P. Cunningham:
Posterior and Computational Uncertainty in Gaussian Processes. NeurIPS 2022 - [c56]Fynn Bachmann, Philipp Hennig, Dmitry Kobak:
Wasserstein t-SNE. ECML/PKDD (1) 2022: 104-120 - [c55]Marius Hobbhahn, Agustinus Kristiadi, Philipp Hennig:
Fast predictive uncertainty for classification with Bayesian deep networks. UAI 2022: 822-832 - [i80]Filip Tronarp, Nathanael Bosch, Philipp Hennig:
Fenrir: Physics-Enhanced Regression for Initial Value Problems. CoRR abs/2202.01287 (2022) - [i79]Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike von Luxburg:
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference. CoRR abs/2203.03353 (2022) - [i78]Fynn Bachmann, Philipp Hennig, Dmitry Kobak:
Wasserstein t-SNE. CoRR abs/2205.07531 (2022) - [i77]Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig:
Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks. CoRR abs/2205.10041 (2022) - [i76]Jonathan Wenger, Geoff Pleiss, Marvin Pförtner, Philipp Hennig, John P. Cunningham:
Posterior and Computational Uncertainty in Gaussian Processes. CoRR abs/2205.15449 (2022) - [i75]Emilia Magnani, Nicholas Krämer, Runa Eschenhagen, Lorenzo Rosasco, Philipp Hennig:
Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs. CoRR abs/2208.01565 (2022) - [i74]Julia Grosse, Cheng Zhang, Philipp Hennig:
Optimistic Optimization of Gaussian Process Samples. CoRR abs/2209.00895 (2022) - [i73]Marvin Pförtner, Ingo Steinwart, Philipp Hennig, Jonathan Wenger:
Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers. CoRR abs/2212.12474 (2022) - 2021
- [j13]Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe:
Robot Learning With Crash Constraints. IEEE Robotics Autom. Lett. 6(2): 1439-1446 (2021) - [j12]Filip Tronarp, Simo Särkkä, Philipp Hennig:
Bayesian ODE solvers: the maximum a posteriori estimate. Stat. Comput. 31(3): 23 (2021) - [c54]Nathanael Bosch, Philipp Hennig, Filip Tronarp:
Calibrated Adaptive Probabilistic ODE Solvers. AISTATS 2021: 3466-3474 - [c53]Katharina Ott, Prateek Katiyar, Philipp Hennig, Michael Tiemann:
ResNet After All: Neural ODEs and Their Numerical Solution. ICLR 2021 - [c52]Filip de Roos, Alexandra Gessner, Philipp Hennig:
High-Dimensional Gaussian Process Inference with Derivatives. ICML 2021: 2535-2545 - [c51]Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis:
Bayesian Quadrature on Riemannian Data Manifolds. ICML 2021: 3459-3468 - [c50]Robin M. Schmidt, Frank Schneider, Philipp Hennig:
Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers. ICML 2021: 9367-9376 - [c49]Nicholas Krämer, Philipp Hennig:
Linear-Time Probabilistic Solution of Boundary Value Problems. NeurIPS 2021: 11160-11171 - [c48]Jonathan Schmidt, Nicholas Krämer, Philipp Hennig:
A Probabilistic State Space Model for Joint Inference from Differential Equations and Data. NeurIPS 2021: 12374-12385 - [c47]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence. NeurIPS 2021: 18789-18800 - [c46]Erik A. Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig:
Laplace Redux - Effortless Bayesian Deep Learning. NeurIPS 2021: 20089-20103 - [c45]Frank Schneider, Felix Dangel, Philipp Hennig:
Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks. NeurIPS 2021: 20825-20837 - [c44]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Learnable uncertainty under Laplace approximations. UAI 2021: 344-353 - [c43]Julia Grosse, Cheng Zhang, Philipp Hennig:
Probabilistic DAG search. UAI 2021: 1424-1433 - [i72]Frank Schneider, Felix Dangel, Philipp Hennig:
Cockpit: A Practical Debugging Tool for Training Deep Neural Networks. CoRR abs/2102.06604 (2021) - [i71]Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis:
Bayesian Quadrature on Riemannian Data Manifolds. CoRR abs/2102.06645 (2021) - [i70]Filip de Roos, Alexandra Gessner, Philipp Hennig:
High-Dimensional Gaussian Process Inference with Derivatives. CoRR abs/2102.07542 (2021) - [i69]Filip de Roos, Carl Jidling, Adrian Wills, Thomas B. Schön, Philipp Hennig:
A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization. CoRR abs/2102.10880 (2021) - [i68]Jonathan Schmidt, Nicholas Krämer, Philipp Hennig:
A Probabilistic State Space Model for Joint Inference from Differential Equations and Data. CoRR abs/2103.10153 (2021) - [i67]Marius Hobbhahn, Philipp Hennig:
Laplace Matching for fast Approximate Inference in Generalized Linear Models. CoRR abs/2105.03109 (2021) - [i66]Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius:
Informed Equation Learning. CoRR abs/2105.06331 (2021) - [i65]Felix Dangel, Lukas Tatzel, Philipp Hennig:
ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure. CoRR abs/2106.02624 (2021) - [i64]Nicholas Krämer, Philipp Hennig:
Linear-Time Probabilistic Solutions of Boundary Value Problems. CoRR abs/2106.07761 (2021) - [i63]Julia Grosse, Cheng Zhang, Philipp Hennig:
Probabilistic DAG Search. CoRR abs/2106.08717 (2021) - [i62]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being a Bit Frequentist Improves Bayesian Neural Networks. CoRR abs/2106.10065 (2021) - [i61]Erik A. Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig:
Laplace Redux - Effortless Bayesian Deep Learning. CoRR abs/2106.14806 (2021) - [i60]Jonathan Wenger, Geoff Pleiss, Philipp Hennig, John P. Cunningham, Jacob R. Gardner:
Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning. CoRR abs/2107.00243 (2021) - [i59]Nathanael Bosch, Filip Tronarp, Philipp Hennig:
Pick-and-Mix Information Operators for Probabilistic ODE Solvers. CoRR abs/2110.10770 (2021) - [i58]Nicholas Krämer, Nathanael Bosch, Jonathan Schmidt, Philipp Hennig:
Probabilistic ODE Solutions in Millions of Dimensions. CoRR abs/2110.11812 (2021) - [i57]Nicholas Krämer, Jonathan Schmidt, Philipp Hennig:
Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations. CoRR abs/2110.11847 (2021) - [i56]Runa Eschenhagen, Erik A. Daxberger, Philipp Hennig, Agustinus Kristiadi:
Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning. CoRR abs/2111.03577 (2021) - [i55]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:
ProbNum: Probabilistic Numerics in Python. CoRR abs/2112.02100 (2021) - [i54]Philipp Hennig, Ilse C. F. Ipsen, Maren Mahsereci, Tim Sullivan:
Probabilistic Numerical Methods - From Theory to Implementation (Dagstuhl Seminar 21432). Dagstuhl Reports 11(9): 102-119 (2021) - 2020
- [j11]Simon Bartels, Philipp Hennig:
Conjugate Gradients for Kernel Machines. J. Mach. Learn. Res. 21: 55:1-55:42 (2020) - [j10]Hans Kersting, Timothy John Sullivan, Philipp Hennig:
Convergence rates of Gaussian ODE filters. Stat. Comput. 30(6): 1791-1816 (2020) - [c42]Felix Dangel, Stefan Harmeling, Philipp Hennig:
Modular Block-diagonal Curvature Approximations for Feedforward Architectures. AISTATS 2020: 799-808 - [c41]Alexandra Gessner, Oindrila Kanjilal, Philipp Hennig:
Integrals over Gaussians under Linear Domain Constraints. AISTATS 2020: 2764-2774 - [c40]Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig:
Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering. ICBINB@NeurIPS 2020: 60-69 - [c39]Felix Dangel, Frederik Kunstner, Philipp Hennig:
BackPACK: Packing more into Backprop. ICLR 2020 - [c38]Hans Kersting, Nicholas Krämer, Martin Schiegg, Christian Daniel, Michael Tiemann, Philipp Hennig:
Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems. ICML 2020: 5198-5208 - [c37]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. ICML 2020: 5436-5446 - [c36]Jonathan Wenger, Philipp Hennig:
Probabilistic Linear Solvers for Machine Learning. NeurIPS 2020 - [i53]Hans Kersting, Nicholas Krämer, Martin Schiegg, Christian Daniel, Michael Tiemann, Philipp Hennig:
Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems. CoRR abs/2002.09301 (2020) - [i52]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. CoRR abs/2002.10118 (2020) - [i51]Marius Hobbhahn, Agustinus Kristiadi, Philipp Hennig:
Fast Predictive Uncertainty for Classification with Bayesian Deep Networks. CoRR abs/2003.01227 (2020) - [i50]Filip Tronarp, Simo Särkkä, Philipp Hennig:
Bayesian ODE Solvers: The Maximum A Posteriori Estimate. CoRR abs/2004.00623 (2020) - [i49]Robin M. Schmidt, Frank Schneider, Philipp Hennig:
Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers. CoRR abs/2007.01547 (2020) - [i48]Katharina Ott, Prateek Katiyar, Philipp Hennig, Michael Tiemann:
When are Neural ODE Solutions Proper ODEs? CoRR abs/2007.15386 (2020) - [i47]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features. CoRR abs/2010.02709 (2020) - [i46]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Learnable Uncertainty under Laplace Approximations. CoRR abs/2010.02720 (2020) - [i45]Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe:
Robot Learning with Crash Constraints. CoRR abs/2010.08669 (2020) - [i44]Jonathan Wenger, Philipp Hennig:
Probabilistic Linear Solvers for Machine Learning. CoRR abs/2010.09691 (2020) - [i43]Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig:
Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering. CoRR abs/2011.04803 (2020) - [i42]Nathanael Bosch, Philipp Hennig, Filip Tronarp:
Calibrated Adaptive Probabilistic ODE Solvers. CoRR abs/2012.08202 (2020) - [i41]Nicholas Krämer, Philipp Hennig:
Stable Implementation of Probabilistic ODE Solvers. CoRR abs/2012.10106 (2020)
2010 – 2019
- 2019
- [j9]Michael Schober, Simo Särkkä, Philipp Hennig:
A probabilistic model for the numerical solution of initial value problems. Stat. Comput. 29(1): 99-122 (2019) - [j8]Simon Bartels, Jon Cockayne, Ilse C. F. Ipsen, Philipp Hennig:
Probabilistic linear solvers: a unifying view. Stat. Comput. 29(6): 1249-1263 (2019) - [j7]Filip Tronarp, Hans Kersting, Simo Särkkä, Philipp Hennig:
Probabilistic solutions to ordinary differential equations as nonlinear Bayesian filtering: a new perspective. Stat. Comput. 29(6): 1297-1315 (2019) - [c35]Filip de Roos, Philipp Hennig:
Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization. AISTATS 2019: 1448-1457 - [c34]Georgios Arvanitidis, Søren Hauberg, Philipp Hennig, Michael Schober:
Fast and Robust Shortest Paths on Manifolds Learned from Data. AISTATS 2019: 1506-1515 - [c33]Frank Schneider, Lukas Balles, Philipp Hennig:
DeepOBS: A Deep Learning Optimizer Benchmark Suite. ICLR (Poster) 2019 - [c32]