Nonparametric estimation of homogenized invariant measures from multiscale data via Hermite expansion

TL;DR

This paper introduces a spectral Hermite expansion method for nonparametric density estimation of invariant measures in multiscale Langevin systems, demonstrating convergence and robustness through theoretical analysis and numerical experiments.

Contribution

It develops a novel Hermite expansion-based spectral estimator for invariant densities in multiscale diffusions, with proven convergence as scale separation vanishes.

Findings

Estimator converges to true invariant density as scale parameter approaches zero.

Method is robust to model parameters and data noise.

Numerical experiments confirm theoretical convergence and accuracy.

Abstract

We consider the problem of density estimation in the context of multiscale Langevin diffusion processes, where a single-scale homogenized surrogate model can be derived. In particular, our aim is to learn the density of the invariant measure of the homogenized dynamics from a continuous-time trajectory generated by the full multiscale system. We propose a spectral method based on a truncated Fourier expansion with Hermite functions as orthonormal basis. The Fourier coefficients are computed directly from the data owing to the ergodic theorem. We prove that the resulting density estimator is robust and converges to the invariant density of the homogenized model as the scale separation parameter vanishes, provided the time horizon and the number of Fourier modes are suitably chosen in relation to the multiscale parameter. The accuracy and reliability of this methodology is further demonstrated through a series of numerical experiments.