The MILES project-team is a joint effort from researchers in theoretical computer science, applied mathematics and game theory. By combining their knowledge, the MILES researchers aim at making significant advances in the field of machine learning and data science, in terms of theoretical foundations as well as in concrete applications.

The MILES project-team is hosted by the LAMSADE research unit at Université Paris Dauphine-PSL, France.

The team is also heavily involved in the Paris Artificial Research Intelligence Institute (prAIrie).

Research interests

  • Theoretical foundations
    • Trustworthy machine learning
      • Robustness against adversarial attacks
      • Privacy preserving models (e.g. differential privacy)
    • Explainable artificial intelligence
      • Causal inference
      • Sparse models
    • Online learning and game theory
    • Reinforcement learning
    • Theory of deep learning
  • Algorithmic aspects
    • Compact and energy efficient deep neural networks
    • High dimensional data streams
    • Optimization methods
    • Sketching and clustering
    • Structured representations for deep learning
  • Applications
    • Health
    • Game playing
    • Robotics
    • Computer vision
    • Art & humanities


  • Université Paris Dauphine-PSL, LAMSADE
  • Place du Maréchal de Lattre de Tassigny,
  • 75 775 PARIS CEDEX 16, FRANCE

Metro line 2 Porte Dauphine, RER line C Avenue Foch.