TOUTELIA 2021 : Statistical Physics, Probability and AI

Liste des contributions

1. Talk by Yann Ollivier

16/12/2021 14:00

This is the conference talk. Yann Ollivier will also give a colloquim talk the next day.

Abstract: Markov decision processes are a model for several artificial intelligence problems, such as games (chess, Go...) or robotics. At each timestep, an agent has to choose an action, then receives a reward, and then the agent's environment changes (deterministically or stochastically) in response...

5. Talk by Sandrine Péché

16/12/2021 15:30

We consider a random matrix model M = YY∗ where Y = (f(WX)_ij) and W and X are large rectangular matrices with iid entries.The function f is called the activation function in certain neural networks.

Pennington and Worah have identified the empirical eigenvalue distribution of such random matrices in the Gaussian case (W and X). We extend their result to a wider class of distributions for...

4. Talk by Franck Gabriel

17/12/2021 09:00

In recent years, randomness has become more important in machine learning. Through two examples, we will see that it can be used to [1] "select" well-behaved regions of parameters and [2] provide an easier optimization problem.

[1] In deep learning, I will present the NTK regime, where, by considering a "wide" random initialization, it can be shown that neural networks with large width...

3. Talk by Marc Lelarge

17/12/2021 10:30

Abstract: Geometric deep learning is an attempt for geometric unification of a broad class of machine learning problems from the perspectives of symmetry and invariance. In this talk, I will present some advances of geometric deep learning applied to combinatorial structures. I will focus on various classes of graph neural networks that have been shown to be successful in a wide range of...

2. COLLOQUIUM by Yann Ollivier

17/12/2021 14:00

Résumé : "Les problèmes de raisonnement inductif ou d'extrapolation comme "deviner la suite d'une série de nombres", ou plus généralement, "comprendre la structure cachée dans des observations", sont fondamentaux si l'on veut un jour construire une intelligence artificielle. On a parfois l'impression que ces problèmes ne sont pas mathématiquement bien définis. Or il existe une théorie...