Parametric model reduction of mean-field and stochastic systems via higher-order action matching
This addresses the need for efficient parameter-dependent predictions in physics simulations, though it is incremental as it builds on existing action matching and optimal transport techniques.
The paper tackles the problem of learning surrogate models for population dynamics in physical systems with stochastic and mean-field effects, achieving accurate predictions over a wide parameter range and outperforming state-of-the-art diffusion-based and flow-based methods.
The aim of this work is to learn models of population dynamics of physical systems that feature stochastic and mean-field effects and that depend on physics parameters. The learned models can act as surrogates of classical numerical models to efficiently predict the system behavior over the physics parameters. Building on the Benamou-Brenier formula from optimal transport and action matching, we use a variational problem to infer parameter- and time-dependent gradient fields that represent approximations of the population dynamics. The inferred gradient fields can then be used to rapidly generate sample trajectories that mimic the dynamics of the physical system on a population level over varying physics parameters. We show that combining Monte Carlo sampling with higher-order quadrature rules is critical for accurately estimating the training objective from sample data and for stabilizing the training process. We demonstrate on Vlasov-Poisson instabilities as well as on high-dimensional particle and chaotic systems that our approach accurately predicts population dynamics over a wide range of parameters and outperforms state-of-the-art diffusion-based and flow-based modeling that simply condition on time and physics parameters.