Modelling, Estimating and Sampling Multiscale Maximum Entropy Distributions in High Dimensions

Quand : 9 juin 2026 à 11:15

Où : 1R2-132

Organisé par : Institut Henri Poincaré

Modelling, estimating and sampling non-Gaussian probability distributions in high dimension from limited data lies at the heart of statistical physics and machine learning. Such distributions describe processes as varied as ocean currents, flocks of birds, or natural images. Classical approaches rely on models that are typically maximum-entropy distributions with few parameters, limited in express