English

Gaussian Approximations for Maxima of Random Vectors under $(2+\iota)$-th Moments

Statistics Theory 2019-05-28 v1 Statistics Theory

Abstract

We derive a Gaussian approximation result for the maximum of a sum of random vectors under (2+ι)(2+\iota)-th moments. Our main theorem is abstract and nonasymptotic, and can be applied to a variety of statistical learning problems. The proof uses the Lindeberg telescopic sum device along with some other newly developed technical results.

Keywords

Cite

@article{arxiv.1905.11014,
  title  = {Gaussian Approximations for Maxima of Random Vectors under $(2+\iota)$-th Moments},
  author = {Qiang Sun},
  journal= {arXiv preprint arXiv:1905.11014},
  year   = {2019}
}

Comments

6 pages, short note