collaborators
Showing math.STShow all

2 papers · 1 filter

math.ST2025

Generalization bounds for score-based generative models: a synthetic proof

Arthur Stéphanovitch, Eddie Aamari, Clément Levrard

We establish minimax convergence rates for score-based generative models (SGMs) under the -Wasserstein distance. Assuming the target density lies in a nonparametric $Î…

math.ST2025

Wasserstein GANs are Minimax Optimal Distribution Estimators

Arthur Stéphanovitch, Eddie Aamari, Clément Levrard

We provide non asymptotic rates of convergence of the Wasserstein Generative Adversarial networks (WGAN) estimator. We build neural networks classes representing the generators and…