Jonathan Wenger

Postdoctoral Research Scientist

Columbia University

About me

I am a postdoctoral research scientist at Columbia University’s Zuckerman Institute working with John P. Cunningham. My research focuses on numerical methods for machine learning, in particular probabilistic numerics which interprets numerical methods as learning procedures. Previously I was a doctoral student in computer science at the University of Tübingen and an IMPRS-IS fellow advised by Philipp Hennig.

Interests

Probabilistic Numerics
Numerical Analysis
Gaussian Processes

Education

Doctoral Degree in Computer Science, 2023
University of Tübingen, IMPRS-IS fellow
MSc in Engineering Physics, 2019
KTH Royal Institute of Technology
MSc in Mathematics, 2019
TU München

Publications

Recent Preprints and Papers

Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference

Model selection in Gaussian processes scales prohibitively with the size of the training dataset, both in time and memory. While many …

Jonathan Wenger, Kaiwen Wu, Philipp Hennig, Jacob R. Gardner, Geoff Pleiss, John P. Cunningham (2024). Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference. NeurIPS.

Computation-Aware Kalman Filtering and Smoothing

Kalman filtering and smoothing are the foundational mechanisms for efficient inference in Gauss-Markov models. However, their time and …

Marvin Pförtner, Jonathan Wenger, Jon Cockayne, Philipp Hennig (2024). Computation-Aware Kalman Filtering and Smoothing. arXiv preprint.

Large-Scale Gaussian Processes via Alternating Projection

Gaussian process (GP) hyperparameter optimization requires repeatedly solving linear systems with n×n kernel matrices. To address the …

Kaiwen Wu, Jonathan Wenger, Haydn Jones, Geoff Pleiss, Jacob R. Gardner (2024). Large-Scale Gaussian Processes via Alternating Projection. AISTATS.

Accelerating Generalized Linear Models by Trading Off Computation for Uncertainty

Bayesian Generalized Linear Models (GLMs) define a flexible probabilistic framework to model categorical, ordinal and continuous data, …

Lukas Tatzel, Jonathan Wenger, Frank Schneider, Philipp Hennig (2023). Accelerating Generalized Linear Models by Trading Off Computation for Uncertainty. arXiv preprint.

On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective

The neural tangent kernel (NTK) has garnered significant attention as a theoretical framework for describing the behavior of …

Jonathan Wenger, Felix Dangel, Agustinus Kristiadi (2023). On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective. arXiv preprint.

See all publications

Talks

Recent and Upcoming

Probabilistic Linear Solvers

Apr 8, 2024 09:00 Southampton, UK

Computation-aware Gaussian Process Inference

Jul 19, 2023 12:00 Cambridge, UK

Probabilistic Numerics for Scientific Machine Learning

Jun 27, 2023 11:10 Würzburg, Germany

Teaching

Classes and Tutorials

Lecture: Numerics of Machine Learning WS2022/23

Tutorial: Data Literacy WS2021/22

Tutorial: Probabilistic Machine Learning SS2021

Projects

Software, Tech Reports, etc.

ProbNum: Probabilistic Numerics in Python

Probabilistic Numerics (PN) interprets classic numerical routines as inference procedures by taking a probabilistic viewpoint. This …

Jonathan Wenger

Code Documentation

Numerical Methods for Time-optimal Control of Linear Systems

In this project we analyzed time-optimal control problems with linear dynamics and numerical methods for solving them. When …

Jonathan Wenger