World's Best Scientists 2026 revealed!

D-Index & Metrics

Engineering and Technology

D-Index
31
Citations
4958
World Ranking
9664
National Ranking
319

Overview

Philipp Hennig is affiliated with the University of Tübingen in Germany. Their academic contributions are primarily situated within the broad field of Computer Science, with a focus on Artificial Intelligence, Statistical and Nonlinear Physics, Statistics, Probability and Uncertainty, Computer Vision and Pattern Recognition, as well as Management Science and Operations Research.

Their research topics span several specialized areas, including:

  • Gaussian Processes and Bayesian Inference
  • Model Reduction and Neural Networks
  • Adversarial Robustness in Machine Learning
  • Probabilistic and Robust Engineering Design
  • Machine Learning and Algorithms
  • Neural Networks and Applications
  • Machine Learning and Data Classification

Philipp Hennig has published extensively, with a significant number of contributions to arXiv (Cornell University), as well as in journals such as Statistics and Computing, Journal of Computational Neuroscience, and publications by Cambridge University Press. Their book publication includes:

  • Probabilistic Numerics, published by Cambridge University Press in 2022

Some recent papers by Philipp Hennig include:

  • Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers, 2020, arXiv (Cornell University)
  • Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks, 2020, arXiv (Cornell University)
  • Laplace Redux -- Effortless Bayesian Deep Learning, 2021, arXiv (Cornell University)
  • Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers, 2022, arXiv (Cornell University)

Frequent co-authors collaborating with Philipp Hennig include:

  • Agustinus Kristiadi
  • Nicholas Krämer
  • Michael A. Osborne
  • Jonathan Schmidt
  • Frank Schneider

The visible pattern in publication venues and research areas indicates a strong engagement with both foundational theoretical work and applied methodologies in machine learning and probabilistic modeling. Contributions to arXiv demonstrate ongoing participation in open-access dissemination of research findings within the computational and statistical research communities.

Best Publications

  • Entropy search for information-efficient global optimization

    Philipp Hennig;Christian J. Schuler

  • Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets

    Aaron Klein;Stefan Falkner;Simon Bartels;Philipp Hennig

  • Dense connectomic reconstruction in layer 4 of the somatosensory cortex

    Alessandro Motta;Manuel Berning;Kevin M. Boergens;Benedikt Staffler

  • Batch Bayesian Optimization via Local Penalization

    Javier Gonzalez;Zhenwen Dai;Philipp Hennig;Neil D. Lawrence

  • Probabilistic numerics and uncertainty in computations

    Philipp Hennig;Michael A. Osborne;Mark A. Girolami

  • Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences.

    Motonobu Kanagawa;Philipp Hennig;Dino Sejdinovic;Bharath K. Sriperumbudur

  • The Randomized Dependence Coefficient

    David Lopez-Paz;Philipp Hennig;Bernhard Schölkopf

  • Automatic LQR tuning based on Gaussian process global optimization

    Alonso Marco;Philipp Hennig;Jeannette Bohg;Stefan Schaal

  • Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets

    Aaron Klein;Stefan Falkner;Simon Bartels;Philipp Hennig

  • Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization

    Alonso Marco;Felix Berkenkamp;Philipp Hennig;Angela P. Schoellig

  • Probabilistic Line Searches for Stochastic Optimization

    Maren Mahsereci;Philipp Hennig

  • Gaussian Process-Based Predictive Control for Periodic Error Correction

    Edgar D. Klenske;Melanie N. Zeilinger;Bernhard Scholkopf;Philipp Hennig

  • Quasi-Newton methods: a new direction

    Philipp Hennig;Martin Kiefel

  • Probabilistic ODE Solvers with Runge-Kutta Means

    Michael Schober;David K Duvenaud;Philipp Hennig

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

    Agustinus Kristiadi;Matthias Hein;Philipp Hennig

  • Active learning of linear embeddings for Gaussian processes

    Roman Garnett;Michael A. Osborne;Philipp Hennig

  • Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature

    Tom Gunter;Michael A Osborne;Roman Garnett;Philipp Hennig

  • Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients

    Lukas Balles;Philipp Hennig

  • Descending through a Crowded Valley — Benchmarking Deep Learning Optimizers

    Robin Marc Schmidt;Frank Schneider;Philipp Hennig

  • Limitations of the empirical Fisher approximation for natural gradient descent

    Frederik Kunstner;Philipp Hennig;Lukas Balles

  • Probabilistic Interpretation of Linear Solvers

    Philipp Hennig

  • A probabilistic model for the numerical solution of initial value problems

    Michael Schober;Simon Särkkä;Philipp Hennig

  • Inference of Cause and Effect with Unsupervised Inverse Regression

    Eleni Sgouritsa;Dominik Janzing;Philipp Hennig;Bernhard Schölkopf

  • Incremental Local Gaussian Regression

    Franziska Meier;Philipp Hennig;Stefan Schaal

  • Gaussian Probabilities and Expectation Propagation

    John P. Cunningham;Philipp Hennig;Simon Lacoste-Julien

  • Fast Bayesian hyperparameter optimization on large datasets

    Aaron Klein;Stefan Falkner;Simon Bartels;Philipp Hennig

  • Early Stopping without a Validation Set.

    Maren Mahsereci;Lukas Balles;Christoph Lassner;Philipp Hennig

Frequent Co-Authors

Bernhard Schölkopf
Bernhard Schölkopf Max Planck Institute for Intelligent Systems
Stefan Schaal
Stefan Schaal Google (United States)
Matthias Hein
Matthias Hein University of Tübingen
Simo Särkkä
Simo Särkkä Aalto University
Thore Graepel
Thore Graepel University College London
David Duvenaud
David Duvenaud University of Toronto
Frank Hutter
Frank Hutter University of Freiburg
Jeannette Bohg
Jeannette Bohg Stanford University
Ralf Herbrich
Ralf Herbrich Hasso Plattner Institute

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Students interested in Engineering and Technology in the USA may benefit from exploring related online degrees to broaden their career options. Many technical roles require a strong grasp of business, management, and organizational skills—areas supported by diverse online programs.

Pursuing a book keeping certificate can be valuable for those aiming to add financial management skills to their technical background. Bookkeeping knowledge is essential in both startups and large organizations, complementing engineering work with practical business skills.

For those looking to build administrative expertise, office administration classes offer foundational training in organizational operations, communication, and office technologies. These skills are highly transferable and support a wide range of technology-driven roles.

If you’re considering leadership or business-oriented positions, earning an online ba business administration can help you bridge technical and managerial responsibilities within engineering fields.

Moreover, advancing to an organizational management degree online prepares you for strategic leadership roles. These programs emphasize team management, communication, and organizational change—crucial elements in today’s tech-driven workplace.

Best Scientists Citing Philipp Hennig

Trending Scientists

Recently Published Articles