Quantitative bounds for high-dimensional non-linear functionals of Gaussian processes

In this paper, we establish explicit quantitative Berry-Esseen bounds in the hyper-rectangle distance $d_R$, the convex distance $d_{\mathscr{C}}$ and the $1$-Wasserstein distance $d_W$ for high-dimensional, non-linear functionals of Gaussian processes, allowing for strong dependence between variables. Our main result demonstrates that, under a smoothness assumption, the convergence rate under $d_R$ is sub-polynomial in the dimension and polynomial under $d_{\mathscr{C}}$ and $d_W$. To the best of our knowledge, our results under $d_R$ provide the first explicit sub-polynomial bound for high-dimensional, non-linear functionals of Gaussian processes beyond the i.i.d. setting. Building on this, we derive explicit Berry-Esseen bounds under both $d_R$ and $d_{\mathscr{C}}$ for multiple statistical examples, such as the method of moments, empirical characteristic functions, empirical moment-generating functions, and functional limit theorems in high-dimensional settings.

💡 Research Summary

This paper establishes explicit Berry–Esseen type bounds for high‑dimensional, non‑linear functionals of Gaussian processes, measured in three probability metrics: the hyper‑rectangle distance (d_R), the convex set distance (d_{\mathscr C}), and the 1‑Wasserstein distance (d_W). The authors consider a sequence of centered stationary Gaussian variables ({G_k}_{k\ge1}) with autocovariance (\rho) and a measurable transformation (\Phi:\mathbb R\to\mathbb R^d). The object of interest is the normalized sum
\