English

Robustly Learning a Gaussian: Getting Optimal Error, Efficiently

Data Structures and Algorithms 2017-11-07 v2 Information Theory Machine Learning math.IT Statistics Theory Machine Learning Statistics Theory

Abstract

We study the fundamental problem of learning the parameters of a high-dimensional Gaussian in the presence of noise -- where an ε\varepsilon-fraction of our samples were chosen by an adversary. We give robust estimators that achieve estimation error O(ε)O(\varepsilon) in the total variation distance, which is optimal up to a universal constant that is independent of the dimension. In the case where just the mean is unknown, our robustness guarantee is optimal up to a factor of 2\sqrt{2} and the running time is polynomial in dd and 1/ϵ1/\epsilon. When both the mean and covariance are unknown, the running time is polynomial in dd and quasipolynomial in 1/ε1/\varepsilon. Moreover all of our algorithms require only a polynomial number of samples. Our work shows that the same sorts of error guarantees that were established over fifty years ago in the one-dimensional setting can also be achieved by efficient algorithms in high-dimensional settings.

Keywords

Cite

@article{arxiv.1704.03866,
  title  = {Robustly Learning a Gaussian: Getting Optimal Error, Efficiently},
  author = {Ilias Diakonikolas and Gautam Kamath and Daniel M. Kane and Jerry Li and Ankur Moitra and Alistair Stewart},
  journal= {arXiv preprint arXiv:1704.03866},
  year   = {2017}
}

Comments

To appear in SODA 2018

R2 v1 2026-06-22T19:15:59.243Z