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

Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates
Vincent Roulet, Siddhartha Srinivasa, Maryam Fazel, Zaid Harchaoui
We present the implementation of nonlinear control algorithms based on linear and quadratic approximations of the objective from a functional viewpoint. We…

An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks
Vincent Roulet, Zaid Harchaoui
We present an approach to obtain convergence guarantees of optimization algorithms for deep networks based on elementary arguments and computations. The…

Differentiable Programming à la Moreau
Vincent Roulet, Zaid Harchaoui
The notion of a Moreau envelope is central to the analysis of first-order optimization algorithms for machine learning. Yet, it has not been developed and…

Target Propagation via Regularized Inversion
Vincent Roulet, Zaid Harchaoui
Target Propagation (TP) algorithms compute targets instead of gradients along neural networks and propagate them backward in a way that is similar yet…

Complexity Bounds of Iterative Linear Quadratic Optimization Algorithms for Discrete Time Nonlinear Control
Vincent Roulet, Siddhartha Srinivasa, Maryam Fazel, Zaid Harchaoui
A classical approach for solving discrete time nonlinear control on a finite horizon consists in repeatedly minimizing linear quadratic approximations of the…

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…

On the Convergence of the Iterative Linear Exponential Quadratic Gaussian Algorithm to Stationary Points
Vincent Roulet, Maryam Fazel, Siddhartha Srinivasa, Zaid Harchaoui
A classical method for risk-sensitive nonlinear control is the iterative linear exponential quadratic Gaussian algorithm. We present its convergence analysis…

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…

Integration Methods and Accelerated Optimization Algorithms
Damien Scieur, Vincent Roulet, Francis Bach, Alexandre d'Aspremont
We show that accelerated optimization methods can be seen as particular instances of multi-step integration schemes from numerical analysis, applied to the…

Learning with Clustering Structure
Vincent Roulet, Fajwel Fogel, Alexandre d'Aspremont, Francis Bach
We study supervised learning problems using clustering constraints to impose structure on either features or samples, seeking to help both prediction and…