Strong Gaussian Approximation for the Sum of Random Vectors

Abstract

This paper derives a new strong Gaussian approximation bound for the sum of independent random vectors. The approach relies on the optimal transport theory and yields explicit dependence on the dimension size p and the sample size n. This dependence establishes a new fundamental limit for all practical applications of statistical learning theory. Particularly, based on this bound, we prove approximation in distribution for the maximum norm in a high-dimensional setting (p > n).

Cite

Text

Buzun et al. "Strong Gaussian Approximation for the Sum of Random Vectors." Conference on Learning Theory, 2022.

Markdown

[Buzun et al. "Strong Gaussian Approximation for the Sum of Random Vectors." Conference on Learning Theory, 2022.](https://mlanthology.org/colt/2022/buzun2022colt-strong/)

BibTeX

@inproceedings{buzun2022colt-strong,
  title     = {{Strong Gaussian Approximation for the Sum of Random Vectors}},
  author    = {Buzun, Nazar and Shvetsov, Nikolay and Dylov, Dmitry V.},
  booktitle = {Conference on Learning Theory},
  year      = {2022},
  pages     = {1693-1715},
  volume    = {178},
  url       = {https://mlanthology.org/colt/2022/buzun2022colt-strong/}
}