Approximating the moments of marginals of high-dimensional distributions

TL;DR

This paper determines the minimal sample size needed to accurately approximate the pth moments of all one-dimensional marginals of high-dimensional distributions, under bounded moment conditions, bridging previous theoretical results.

Contribution

It establishes the optimal sample size bound of O(n^{p/2}) for approximating marginals' moments, improving upon prior bounds with logarithmic factors or stronger assumptions.

Findings

Optimal sample size N=O(n^{p/2}) for p > 2

Bridges gap between previous results with different assumptions

Requires marginals to have bounded 4p moments

Abstract

For probability distributions on $\mathbb{R}^n$, we study the optimal sample size N = N(n,p) that suffices to uniformly approximate the pth moments of all one-dimensional marginals. Under the assumption that the marginals have bounded 4p moments, we obtain the optimal bound $N=O(n^{p/2})$ for p > 2. This bound goes in the direction of bridging the two recent results: a theorem of Guedon and Rudelson [Adv. Math. 208 (2007) 798-823] which has an extra logarithmic factor in the sample size, and a result of Adamczak et al. [J. Amer. Math. Soc. 23 (2010) 535-561] which requires stronger subexponential moment assumptions.