Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
Florentin Coeurdoux, Grégoire Ferré, Jean-Philippe Bouchaud
Empirical studies of trained models often report a transient regime in which signal is detectable in a finite gradient descent time window before overfitting dominates. We provide…
stat.ML2026
Probing the Geometry of Diffusion Models with the String Method
Elio Moreau, Florentin Coeurdoux, Grégoire Ferre +1
Understanding the geometry of learned distributions is fundamental to improving and interpreting diffusion models, yet systematic tools for exploring their landscape remain limited…
stat.ML2026
MGD: Moment Guided Diffusion for Maximum Entropy Generation
Etienne Lempereur, Nathanaël Cuvelle--Magar, Florentin Coeurdoux +2
Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from…