Portrait de Damien Scieur n'est pas disponible

Damien Scieur

scieurda@mila.quebec
Visiteur de recherche indépendant - Samsung SAIT
Superviseur⋅e principal⋅e
Simon Lacoste-Julien
Site web
Google Scholar

Publications

Only tails matter: Average-Case Universality and Robustness in the Convex Regime
Leonardo Cunha
Gauthier Gidel
Fabian Pedregosa
Damien Scieur
Courtney Paquette
2022-06-28
Proceedings of the 39th International Conference on Machine Learning (publié)
doi.org
openreview.net
Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime
Leonardo Cunha
Gauthier Gidel
Fabian Pedregosa
Damien Scieur
Courtney Paquette
2022-06-20
ArXiv (prépublication)
doi.org
openreview.net
Accelerating Smooth Games by Manipulating Spectral Shapes
Waiss Azizian
Damien Scieur
Ioannis Mitliagkas
Simon Lacoste-Julien
Gauthier Gidel
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (publié)
proceedings.mlr.press
arxiv.org
Accelerating Smooth Games by Manipulating Spectral Shapes
Waiss Azizian
Damien Scieur
Ioannis Mitliagkas
Simon Lacoste-Julien
Gauthier Gidel
We use matrix iteration theory to characterize acceleration in smooth games. We define the spectral shape of a family of games as the set co… (voir plus)ntaining all eigenvalues of the Jacobians of standard gradient dynamics in the family. Shapes restricted to the real line represent well-understood classes of problems, like minimization. Shapes spanning the complex plane capture the added numerical challenges in solving smooth games. In this framework, we describe gradient-based methods, such as extragradient, as transformations on the spectral shape. Using this perspective, we propose an optimal algorithm for bilinear games. For smooth and strongly monotone operators, we identify a continuum between convex minimization, where acceleration is possible using Polyak's momentum, and the worst case where gradient descent is optimal. Finally, going beyond first-order methods, we propose an accelerated version of consensus optimization.
2020-01-02
ArXiv (preprint)
arxiv.org
arxiv.org