3 papers
cs.LG2026
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna
To understand the training dynamics of neural networks, prior studies have considered the mean-field limit of two-layer neural networks as the width tends to infinity, establishing…
cs.LG2025
Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden
A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), ena…
math.OC2025
Extreme event probability estimation using PDE-constrained optimization and large deviation theory, with application to tsunamis
Shanyin Tong, Eric Vanden-Eijnden, Georg Stadler
We propose and compare methods for the analysis of extreme events in complex systems governed by PDEs that involve random parameters, in situations where we are interested in quant…