I am a Phd student at Inria Grenoble-Alpes and Criteo AI Lab, and I am defending my PhD in January 2026.
I work under the supervision of Julyan Arbel (Inria Statify), Pierre Gaillard (Inria Thoth), and Thibaud Rahier (Criteo AI Lab).

I am doing Theoretical Machine Learning, Optimization, Probability, Statistics.
My current research is focused on Online Learning, Bandits Theory. I like theoretical guarantees in general (and PAC ones when possible).

Currently Looking for opportunities.
I hope to continue doing research, maybe a little more applied but keeping a theoretical flavor. Don’t hesitate to reach out.

I am always happy to learn new things.
CV Here!

Events/Talks

Future: Defending my PhD on 20/01/2026.
Past:

• PAISS(Summer School), 01/09/2025-05/09/2025
• Visiting scholar at University of Tubingen, Lifelong Reinforcement Learning Group, 04/2025-06/2025
• ALT2025, 24/02/2025-27/02/2025
• NeurIPS2024, 10/12/2024-15/12/2024
• NeurIPS @ Paris, 04/12/2024-05/12/2024
• Invited talk at University of Amsterdam about Submodular Optimization with Bandit feedbacks, 21/10/2024
• ICML2024, 21/07/2024-27/07/2024
• Journées de Statistique de la SFdS, 27/05/2024-31/05/2024
• Reinforcement Learning Summer School, 26/06/2023-05/07/2023

Contact

Always interested in potential opportunities, new subjects, discussions, memes…
zj.zhoujulien@gmail.com