Philipp Hennig

Department of Empirical Inference, Max Planck Institute for Intelligent Systems, Tübingen, Germany

Show Academic Trajectory

Ego Network

D-Core

Research Interests

Author Statistics

Experience

Education

Bio

None

Papers91 papers

Sort

By YearBy Citation

Robot Learning with Crash Constraints

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

international conference on robotics and automation, no. 2 (2021): 1439-1446

Bibtex

Bayesian ODE Solvers: The Maximum A Posteriori Estimate

Tronarp Filip, Sarkka Simo,Hennig Philipp

Stat. Comput., no. 3 (2021): 23

EIBibtex

Calibrated Adaptive Probabilistic ODE Solvers

Nathanael Bosch,Philipp Hennig, Filip Tronarp

AISTATS, pp.3466-3474, (2021)

EIBibtex

BackPACK: Packing more into Backprop

Felix Dangel, Frederik Kunstner,Philipp Hennig

ICLR, (2020)

EIBibtex

Convergence rates of Gaussian ODE filters

Hans Kersting, T J Sullivan,Philipp Hennig

STATISTICS AND COMPUTING, no. 6 (2020): 1791-1816

WOSEIBibtex

Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering

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

Bibtex

ResNet After All: Neural ODEs and Their Numerical Solution

Katharina Ott, Prateek Katiyar,Philipp Hennig, Michael Tiemann

international conference on learning representations, (2020)

Bibtex

Probabilistic Linear Solvers for Machine Learning

Jonathan Wenger,Philipp Hennig

NIPS 2020, (2020)

EIBibtex

When are Neural ODE Solutions Proper ODEs

Katharina Ott, Prateek Katiyar,Philipp Hennig, Michael Tiemann

Bibtex

Descending through a Crowded Valley -- Benchmarking Deep Learning Optimizers

Robin M. Schmidt, Frank Schneider,Philipp Hennig

Bibtex

Modular Block-diagonal Curvature Approximations for Feedforward Architectures

Felix Dangel, Stefan Harmeling,Philipp Hennig

AISTATS, pp.799-808, (2020)

EIBibtex

Stable Implementation of Probabilistic ODE Solvers

Nicholas Krämer,Philipp Hennig

Bibtex

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

Kersting Hans, Krämer Nicholas,Schiegg Martin, Daniel Christian, Tiemann Michael,Hennig Philipp

ICML, pp.5198-5208, (2020)

Cited by1EIBibtex

Analytical probabilistic modeling of dose-volume histograms

Wahl Niklas,Hennig Philipp, Wieser Hans-Peter,Bangert Mark

Medical physics, (2020)

WOSBibtex

Fast and Robust Shortest Paths on Manifolds Learned from Data

Georgios Arvanitidis, Søren Hauberg,Philipp Hennig,Michael Schober

international conference on artificial intelligence and statistics, (2019)

Cited by6EIBibtex

Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties

Marco Alonso, Baumann Dominik,Hennig Philipp,Trimpe Sebastian

Bibtex

Conjugate Gradients for Kernel Machines

Bartels Simon,Hennig Philipp

Journal of Machine Learning Research, no. 55 (2019): 1-42

EIBibtex

Limitations of the empirical Fisher approximation for natural gradient descent

Frederik Kunstner,Philipp Hennig, Lukas Balles

NeurIPS, pp.4158-4169, (2019)

Cited by2EIBibtex

Limitations of the Empirical Fisher Approximation for Natural Gradient Descent

Frederik Kunstner, Lukas Balles,Philipp Hennig

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019)

Bibtex

Limitations of the empirical Fisher approximation

Frederik Kunstner,Philipp Hennig, Lukas Balles

neural information processing systems, (2019)

Bibtex

View All

Base Info Papers Patents Projects

Philipp HennigBinding

Papers91 papers

Philipp Hennig