Sharp $L^q$-Convergence Rate in $p$-Wasserstein Distance for Empirical Measures of Diffusion Processes

التفاصيل البيبلوغرافية
العنوان: Sharp $L^q$-Convergence Rate in $p$-Wasserstein Distance for Empirical Measures of Diffusion Processes
المؤلفون: Wang, Feng-Yu, Wu, Bingyao, Zhu, Jie-Xiang
سنة النشر: 2024
المجموعة: Mathematics
مصطلحات موضوعية: Mathematics - Probability
الوصف: For a class of (non-symmetric) diffusion processes on a length space, which in particular include the (reflecting) diffusion processes on a connected compact Riemannian manifold, the exact convergence rate is derived for $({\mathbb E} [{\mathbb W}_p^q(\mu_T,\mu)])^{\frac{1}{q}} (T \to \infty)$ uniformly in $(p,q)\in [1,\infty) \times (0,\infty)$, where $\mu_T$ is the empirical measure of the diffusion process, $\mu$ is the unique invariant probability measure, and ${\mathbb W}_p$ is the $p$-Wasserstein distance. Moreover, when the dimension parameter is less than $4$, we prove that ${\mathbb E} |T {\mathbb W}_2^2(\mu_T,\mu)-\Xi(T)|^q \to 0$ as $T\to\infty$ for any $q\ge 1$, where $\Xi(T)$ is explicitly given by eigenvalues and eigenfunctions for the symmetric part of the generator.
نوع الوثيقة: Working Paper
URL الوصول: http://arxiv.org/abs/2408.09116
رقم الانضمام: edsarx.2408.09116
قاعدة البيانات: arXiv