Pierre Marion

I am a research faculty at INRIA within the SIERRA team, which is a joint team between CNRS, Ecole Normale Supérieure and INRIA. I was previously in 2024-25 a postdoctoral researcher at EPFL under the supervision of Lénaïc Chizat, and before that a PhD student at Sorbonne Université under the supervision of Gérard Biau and Jean-Philippe Vert. My research interests regard the theory of deep learning with an emphasis on generative models and optimization dynamics of neural networks, as well as AI for maths and reasoning.

I am concerned by climate change, hence I strive to fly less and build viable alternatives to frequent intercontinental travel for the research community. Please see details on this webpage.

I currently serve as Paris Satellite Chair for NeurIPS 2026.

Contact: firstname.lastname@inria.fr

Team

If you are interested in working with me, please send me an email with a CV and transcript. I apologize in advance if I do not answer. I hold 1:1 coffee chats for master students, PhD students, or postdocs self-identifying as coming from a minority group or underprivileged backgrounds, to discuss about careers in academia. If you are interested, please send me an email with "coffee chat" in the title.

Current

• Adam Perbost (M2 intern, 2026), co-supervised with Francis Bach.
• Alexandre Jiao (M1 intern, 2026).
• Alexandre Dussolle (M1 intern, 2026).
• Gaëtan Narozniak (PhD, 2025-), co-supervised with Gérard Biau and Rémi Munos.
• Yu-Han Wu (M2, 2023; PhD, 2024-), co-supervised with Quentin Berthet, Gérard Biau, and Claire Boyer.

Alumni

• Seorim Park (MSc, 2024), co-supervised with Lénaïc Chizat.
• Yerkin Yesbay (MSc, 2024), co-supervised with Lénaïc Chizat. Moved to Télécom Paris as a PhD student.
• Nathan Doumèche (M2, 2021), co-supervised with Gérard Biau and Adeline Fermanian. Moved to Sorbonne Université and EDF as a PhD student.

Some thoughts (proto-blog?)

• 2026/02/12: An Attempt at "First Proof".
• 2025/12/08: On the way back from EurIPS 2025.
• 2025/07/18: Towards decentralized ML conferences.
• 2023/10/03: Why I am not attending NeurIPS 2023 in person.