François Rozet

Hi, my name is François! I am a PhD student in deep learning under the supervision of Prof. Gilles Louppe at the University of Liège in Belgium. My research consists in developing and applying deep learning methods to Bayesian inference problems in large-scale dynamical systems (oceans, atmospheres, ...). I am interested in many topics, including generative modeling, inverse problems, and physics emulation, both from an application and theoretical perspective.

I am also passionate about software development and open-source software. I regularly contribute to open-source projects and have published several libraries with thousands of daily users such as Zuko, PIQA and Inox.

For more information about my background, take a look at my resume!

Here follows a list of selected publications. For the full list, see my scholar page.

1. The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning

   Ohana et al. in Advances in Neural Information Processing Systems (2024)

   https://openreview.net/forum?id=00Sx577BT3

2. Learning Diffusion Priors from Observations by Expectation Maximization

   Rozet, Andry, Lanusse, and Louppe in Advances in Neural Information Processing Systems (2024)

   https://openreview.net/forum?id=7v88Fh6iSM

3. Score-based Data Assimilation for a Two-Layer Quasi-Geostrophic Model

   Rozet and Louppe in Machine Learning and the Physical Sciences Workshop (2023)

   https://arxiv.org/abs/2310.01853

4. Score-based Data Assimilation

   Rozet and Louppe in Advances in Neural Information Processing Systems (2023)

   https://openreview.net/forum?id=VUvLSnMZdX

5. Neural posterior estimation for exoplanetary atmospheric retrieval

   Vasist, Rozet, Absil, Mollière, Nasedkin and Louppe in Astronomy & Astrophysics (2023)

   https://arxiv.org/abs/2301.06575

6. Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation

   Delaunoy, Hermans,Rozet, Wehenkel and Louppe in Advances in Neural Information Processing Systems (2022)

   https://openreview.net/forum?id=o762mMj4XK

7. A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithful

   Hermans, Delaunoy, Rozet, Wehenkel and Louppe in Transactions on Machine Learning Research (2022)

   https://openreview.net/forum?id=LHAbHkt6Aq

8. Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference

   Rozet and Louppe in Machine Learning and the Physical Sciences Workshop (2021)

   https://arxiv.org/abs/2110.00449