Machine learning and simulation of stochastic dynamics with applications in materials science, September 2023

This workshop aims to bring together researchers from applied mathematics and computational chemistry working on machine learning methods and related computational approaches for (or with applications in) materials science.

A particular focus of this workshop will be on methods and mathematical theory that relate to the learning and simulation of (stochastic) dynamics of particle systems including dynamics-preserving coarse-graining techniques, learnable equivariant representations of physical quantities beyond machine-learned interatomic potentials (MLIP), and algorithm design for efficient numerical simulation of relevant dynamics.

The workshop website may be found here.