Days (except wednesday) are organized around two sessions: the morning session from 9:00am to 12:00am and a session at the end of afternoon from 4:45pm to 6:45pm. The afternoon is free for scientific discussions, possibly on skis.





  • 16:30 - 18:30    Poster session (followed by a banquet)
    • Jason Altschuler  Fast approximation algorithms for Sinkhorn distances
    • Alberto Bietti  Invariance, Stability, and Complexity of Deep Convolutional Representations
    • Nicolas Boumal  Iteration complexity of optimization on smooth manifolds
    • Arnak Dalalyan   Lasso is minimax rate optimal in robust estimation
    • Darina Dvinskikh  Distributed decentralized (stochastic) optimization for dual friendly functions
    • Pavel Dvurechensky  Distributed optimization for Wasserstein barycenter
    • Aude Genevay  Sinkhorn Divergences: Bridging the gap between Optimal Transport and MMD
    • Dmitry Grishchenko  Identify and Sparsify: Distributed Optimization with Asynchronous Moderate Communications
    • Julien Mairal  Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise
    • Tyler Maunu  Robust Subspace Recovery with Adversarial Outliers
    • Mohamed Ndaoud  Scaled minimax optimality in high-dimensional regression: A non-convex algorithmic regularization approach
    • Dmitrii Ostrovskii  Affine Invariant Covariance Estimation for Heavy-Tailed Distributions
    • Edouard Pauwels  Relating Leverage Scores and Density using Regularized Christoffel Functions
    • Loucas Pillaud-Vivien  Two theoretical results on Stochastic Gradient Descent
    • Krishna Pillutla  A Smoother Way to Train Structured Prediction Models
    • Lorenzo Rosasco  SGD: bridging theory and practice
    • Damien Scieur  Generalized Framework for Nonlinear Acceleration
    • Soledad Villar  Learning quadratic assignment with graph neural networks
    • Jonathan Weed  Wasserstein Projection Pursuit
    • Masashi Sugiyama  Activities of Machine Learning Team at RIKEN Center for Advanced Intelligence Project in Japan
    • Simon Lacoste-Julien  A Variational Inequality Perspective on Generative Adversarial Networks
    • Vianney Perchet  A Problem-Adaptive Algorithm for Resource Allocation
    • François-Pierre Paty  Subspace Robust Wasserstein Distances