Measure estimation on a manifold explored by a diffusion process

Abstract

From the observation of a diffusion path $(X_t{)}_{t\in [0,T]}$ on a compact connected $d$-dimensional manifold $\mathcal{M}$ without boundary, we consider the problem of estimating the stationary measure $\mu$ of the process. Wang and Zhu (2023) showed that for the Wasserstein metric ${\mathcal{W}}_2$ and for $d\ge 5$, the convergence rate of $T^{-1/(d-2)}$ is attained by the occupation measure of the path $(X_t{)}_{t\in [0,T]}$ when $(X_t{)}_{t\in [0,T]}$ is a Langevin diffusion. We extend their result in several directions. First, we show that the rate of convergence holds for a large class of diffusion paths, whose generators are uniformly elliptic. Second, the regularity of the density $p$ of the stationary measure $\mu$ with respect to the volume measure of $\mathcal{M}$ can be leveraged to obtain faster estimators: when $p$ belongs to a Sobolev space of order $\ell \ge 2$, smoothing the occupation measure by convolution with a kernel yields an estimator whose rate of convergence is of order $T^{-(\ell +1)/(2\ell +d-2)}$. We further show that this rate is the minimax rate of estimation for this problem.

References in corpus (5)

• Empirical graph Laplacian approximation of Laplace--Beltrami operators: Large sample results
• Asymptotic statistical equivalence for ergodic diffusions: the multidimensional case
• Manifold estimation and singular deconvolution under Hausdorff loss
• Ergodic approximation of the distribution of a stationary diffusion : rate of convergence
• Estimating the reach of a manifold via its convexity defect function