326 Sherrerd Hall,
I am a fourth-year Ph.D. student in the ORFE Department at Princeton University where I am fortunate to be advised by Prof. Yoram Singer and Prof. Joan Bruna.
Prior to that, I obtained a B.S. in Computer Science from Ecole Normale Superieure de Lyon and a M.S. in Applied Mathematics (Master MVA) from Ecole Normale Superieure Paris-Saclay. More details can be found in my CV.
My main research interests are in deep learning optimization and game optimization. I am also interested in game theory in general and its intersection with deep learning.
Publications & PreprintsDepth separation beyond radial functions
Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization
Dual Averaging is Surprisingly Effective for Deep Learning Optimization
Auction Learning as a two-player game
A Permutation-Equivariant Neural Network Architecture For Auction Design
A mean-field analysis of two-player zero-sum games
Extra-gradient with player sampling for provable fast convergence in n-player games
Towards closing the gap between the theory and practice of SVRG
Global convergence of neuron birth-death dynamics
Smoothed analysis of the low-rank approach for smooth semidefinite programs
NeurIPS 2018 (Oral presentation)
10/2019: Smoothed analysis for some machine learning problems. Google Brain, Montreal, Canada.
02/2019: Global Convergence of the neuron birth-death dynamics. Math and Deep Learning seminar at New York University, USA.
12/2018: Smoothed analysis of the low-rank approach for smooth semidefinite programs. Oral presentation at the NeurIPS conference, Montreal, Canada.
11/2018: Handling non-convexity in low rank approaches for semidefinite programming. MIC seminar at New York University, USA.