Joris Bierkens

Joris Bierkens is an Associate Professor in Statistics at the Delft Institute of Applied Mathematics, Delft University of Technology (TU Delft), and a Visiting Associate Professor at the University of Warwick. His research focuses on computational challenges in Bayesian statistics and statistical physics, particularly through the development and analysis of Markov Chain Monte Carlo (MCMC) methods based on Piecewise Deterministic Markov Processes (PDMPs).

His research interests include Bayesian inference, stochastic processes, probabilistic computation, and Monte Carlo methods. He is particularly known for his work on the Zig-Zag and Boomerang samplers, which offer efficient alternatives to traditional MCMC in high-dimensional and complex settings. These methods are applied in statistical learning, physics, and industrial R&D.

The recent publications highlight a strong trend in theoretical and applied aspects of PDMP-based sampling, including scaling analysis, boundary conditions, infinite-dimensional extensions, and federated computation. Keywords across articles include Bayesian statistics, applied probability, and computational mathematics, with subfields ranging from high-dimensional inference to molecular dynamics and diffusion bridges.

• Associate Editor, Applied Probability Trust (Journal of Applied Probability, Advances in Applied Probability)

Joris Bierkens advises BSc and MSc students on research projects in MCMC, stochastic processes, and probabilistic computation. He collaborates with industry on Bayesian modeling and MCMC applications. His research is supported by academic collaborations and public dissemination through arXiv, GitHub, and open-access journals.

He is a key member of the applied mathematics team at TU Delft, contributing to both theoretical developments and practical implementations of novel sampling algorithms. His work bridges applied mathematics, statistics, and machine learning, with software implementations available on GitHub for reproducibility.