My main research interests are in optimization, neural networks and reinforcement learning. Currently, I focus on improving the speed and memory of optimization solvers using sketching-based methods, and on the understanding of neural network through a convex perspective. Previously, I developed reinforcement and imitation learning algorithms for safety-critical applications.
I obtained a B.S. and M.S. at the Ecole Polytechnique, and I completed the Part III of the Mathematical Tripos at Cambridge University. I was also a visiting student researcher at UC Berkeley with Laurent El Ghaoui.