31 citations · 40 across the 30 of their papers we have counts for
6 papers · 1 filter
Learning to Sample Better
Michael S. Albergo, Eric Vanden-Eijnden
These lecture notes provide an introduction to recent advances in generative modeling methods based on the dynamical transportation of measures, by means of which samples from a si…
Multimarginal generative modeling with stochastic interpolants
Michael S. Albergo, Nicholas M. Boffi, Michael Lindsey +1
Given a set of probability densities, we consider the multimarginal generative modeling problem of learning a joint distribution that recovers these densities as marginals. The…
Stochastic interpolants with data-dependent couplings
Michael S. Albergo, Mark Goldstein, Nicholas M. Boffi +2
Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities. Conventionally, o…
Analysis of learning a flow-based generative model from limited sample complexity
Hugo Cui, Florent Krzakala, Eric Vanden-Eijnden +1
We study the problem of training a flow-based generative model, parametrized by a two-layer autoencoder, to sample from a high-dimensional Gaussian mixture. We provide a sharp end-…
Unveiling the Phase Diagram and Reaction Paths of the Active Model B with the Deep Minimum Action Method
Ruben Zakine, Eric Simonnet, Eric Vanden-Eijnden
Nonequilibrium phase transitions are notably difficult to analyze because their mechanisms depend on the system's dynamics in a complex way due to the lack of time-reversal symmetr…
Deep learning probability flows and entropy production rates in active matter
Nicholas M. Boffi, Eric Vanden-Eijnden
Active matter systems, from self-propelled colloids to motile bacteria, are characterized by the conversion of free energy into useful work at the microscopic scale. They involve p…