Smooth game optimization for machine learning

Unified analyses and accelerated methods for differentiable games.

We also tackled the question of possible acceleration of these methods, providing both lower-bounds for general classes of games and the first momentum-accelerated methods for games by leveraging matrix iteration theory (AISTATS 20).

publications

  1. Accelerating smooth games by manipulating spectral shapes
    Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, and 2 more authors
    In AISTATS, 2020
    arXiv
  2. A tight and unified analysis of gradient-based methods for a whole spectrum of differentiable games
    Waïss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien, and 1 more author
    In AISTATS, 2020
    arXiv Slides
  3. Linear lower bounds and conditioning of differentiable games
    Adam Ibrahim, Waïss Azizian, Gauthier Gidel, and 1 more author
    In ICML, 2020
    arXiv