Abstract
Nonasymptotic bounds for Gaussian and bootstrap approximation have recently attracted significant interest in high-dimensional statistics. This paper studies Berry–Esseen bounds for such approximations with respect to the multivariate Kolmogorov distance, in the context of a sum of n random vectors that are p-dimensional and i.i.d. Up to now, a growing line of work has established bounds with mild logarithmic dependence on p. However, the problem of developing corresponding bounds with near dependence on n has remained largely unresolved. Within the setting of random vectors that have sub-Gaussian or subexponential entries, this paper establishes bounds with near dependence, for both Gaussian and bootstrap approximation. In addition, the proofs are considerably distinct from other recent approaches, and make use of an “implicit smoothing” operation in the Lindeberg interpolation.
Funding Statement
The author was supported in part by NSF Grant DMS-1915786.
Citation
Miles E. Lopes. "Central limit theorem and bootstrap approximation in high dimensions: Near rates via implicit smoothing." Ann. Statist. 50 (5) 2492 - 2513, October 2022. https://doi.org/10.1214/22-AOS2184
Information