Anti-concentration of polynomials: dimension-free covariance bounds and decay of Fourier coefficients

TL;DR

This paper investigates the covariance structure of polynomial functions of random vectors, establishing dimension-free bounds for independent variables and extending results to isotropic Lp balls, with applications to anti-concentration and Fourier decay.

Contribution

It provides new dimension-free covariance bounds for polynomial functions of random vectors, including cases with dependent variables and geometric measures, and links anti-concentration to Fourier coefficient decay.

Findings

Dimension-free covariance bounds for independent variables

Extension of bounds to isotropic Lp balls

High-dimensional van der Corput lemma for Fourier decay

Abstract

We study random variables of the form $f(X)$, when $f$ is a degree $d$ polynomial, and $X$ is a random vector on $\mathbb{R}^{n}$, motivated towards a deeper understanding of the covariance structure of $X^{\otimes d}$. For applications, the main interest is to bound $\mathrm{Var}(f(X))$ from below, assuming a suitable normalization on the coefficients of $f$. Our first result applies when $X$ has independent coordinates, and we establish dimension-free bounds. We also show that the assumption of independence can be relaxed and that our bounds carry over to uniform measures on isotropic $L_{p}$ balls. Moreover, in the case of the Euclidean ball, we provide an orthogonal decomposition of $\mathrm{Cov}(X^{\otimes d})$. Finally, we utilize the connection between anti-concentration and decay of Fourier coefficients to prove a high-dimensional analogue of the van der Corput lemma, thus partially answering a question posed by Carbery and Wright.