Vincent Roulet

Acting Assistant Professor, University of Washington


Email vroulet@uw.edu
UW Box Number 354322
Homepage Personal Home Page 
ORCID iD  0000-0001-6526-5235 

Bio:
Vincent Roulet is an Acting Instructor in the Department of Statistics at the University of Washington. Previously, he was a Postdoctoral fellow in the Department of Statistics at the University of Washington, working with the Algorithmic Foundations for Data Science Institute (ADSI) members Zaid Harchaoui, Dmitriy Drusvyatskiy, Maryam Fazel, and Sham Kakade. He received his Ph.D. from Ecole Normale Superieure Ulm (Paris, France) under the supervision of Alexandre d’Aspremont, working in the Sierra team led by Francis Bach. During his thesis, he worked on mathematical optimization approaches for statistical problems with an underlying combinatorial structure and on the acceleration of optimization algorithms by restarts. He is now working on non-linear dynamical problems such as non-linear control problems and deep learning problems. 

Preprints

Sharpness, Restart and Acceleration
Vincent Roulet, Alexandre d'Aspremont
The {\L}ojasiewicz inequality shows that sharpness bounds on the minimum of convex optimization problems hold almost generically. Sharpness directly controls…

Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
Vincent Roulet, Siddhartha Srinivasa, Dmitriy Drusvyatskiy, Zaid Harchaoui
We examine popular gradient-based algorithms for nonlinear control in the light of the modern complexity analysis of first-order optimization algorithms. The…

Computational Complexity versus Statistical Performance on Sparse Recovery Problems
Vincent Roulet, Nicolas Boumal, Alexandre d'Aspremont
We show that several classical quantities controlling compressed sensing performance directly match classical parameters controlling algorithmic complexity. We…