About

Currently, I am a permanent researcher at Inria Saclay within the TAU team, where my research interests encompass a broad spectrum, with a particular focus on reinforcement learning, AI4Science, and the efficient training of neural networks.
During my previous postdoctoral position in the Scool team, I explored the application of Physics-Informed Neural Networks to tackle Hamilton-Jacobi-Bellman equations in Continuous-Time Reinforcement Learning problems. I also delved into Entropy Regularised Reinforcement Learning and developed methods for comparing reinforcement learning algorithms.
Before, I completed my PhD in Computer Science in University of Bordeaux and Inria Bordeaux. During my PhD, I was working on the topics at the convergence between High Performance Computing (HPC) and Artificial Intelligence (AI). My primary objective during this period was to investigate strategies for memory efficient training of deep neural networks. My thesis, titled ‘Memory Saving Strategies for Deep Neural Network Training’, was supervised by Dr. Olivier Beaumont and Dr. Alexis Joly.

Check out my CV if you want to learn more.

News