My name is Jonas Latz; welcome to my webpage!
I am currently a Lecturer in Applied Mathematics at the University of Manchester.
The research I am involved in is at the interface of statistics and probability, numerical analysis, and computational science. It focuses on methods that can be used to blend mathematical models with observational data. Recently, I have been studying Bayesian and deterministic inverse problems, hierarchical random fields, the theoretical foundations of stochastic optimisation, efficient computational methods in data science and uncertainty quantification, and related problems.
I have an open PhD position. Take a look and contact me!
News
- February 2026: Elliot Addy, Aretha Teckentrup, and I have just published an article on length-scale informed sparse grids for high-dimensional kernel/GP regression in Numerische Mathematik.
- February 2026: New preprint on the data-driven discovery of chemical reaction networks (with Abraham Reyes-Velazquez, Stefan Güttel, and Igor Larrosa)
- November 2025: My article on the random timestep Euler method and its continuous dynamics just appeared in the IMA Journal of Numerical Analysis.
- November 2025: I feel fortunate and honoured to be selected for the John Todd Award 2025 by Oberwolfach Foundation and Mathematisches Forschungszentrum Oberwolfach in Germany.
- September 2025: Our paper on ‘Losing Momentum in Continuous-time Stochastic Optimisation’ (with Kexin Jin, Chenguang Liu, and Alessandro Scagliotti) has just appeared in JMLR; click here to take a look,
- July 2025: I have written a short note on optimisation methods in machine learning, a related children’s game, and AI education.
- June 2025: Would you like to employ GP regression in very high dimensions? Take a look at length scale-informed sparse grids; new preprint with Elliot Addy and Aretha Teckentrup.
- June 2025: The Philosophical Transactions of the Royal Society A have published a theme issue on ‘Partial differential equations in data science’; I happen to be one of the guest editors, alongside Andrea Bertozzi, Nadejda Drenska, and Matthew Thorpe. As part of this, we also published an overview article.
- May 2025: The ProbAI Hub is organising a Winter School on the ‘Mathematical Foundations of AI’; January 5th – 8th 2026 at the University of Warwick, UK. Click here for more information.
- April 2025: Alix Leroy was chosen to be one of 30 participants for the Rising Stars in Computational & Data Sciences meeting at the Oden Institute, University of Texas at Austin, USA. Congratulations! (Photo)
- April 2025: Simon Urbainczyk wins the SIAM Student Poster Prize at the SIAM UKIE Annual Meeting 2025. Congratulations! (Photo)
- April 2025: New preprint on discrete-to-continuum limits of semilinear stochastic evolution equations in Banach spaces by Yves van Gennip, Joshua Willems, and myself.
- March 2025: Our article on Bayesian adversarial robustness just appeared in the European Journal of Applied Mathematics (with Zihan Ding, Kexin Jin, and Chenguang Liu).
