Nearly Tight Sample Complexity Bounds for Learning Mixtures of Gaussians via Sample Compression Schemes

Abstract

We prove that ϴ(k d^2 / ε^2) samples are necessary and sufficient for learning a mixture of k Gaussians in R^d, up to error ε in total variation distance. This improves both the known upper bounds and lower bounds for this problem. For mixtures of axis-aligned Gaussians, we show that O(k d / ε^2) samples suffice, matching a known lower bound. The upper bound is based on a novel technique for distribution learning based on a notion of sample compression. Any class of distributions that allows such a sample compression scheme can also be learned with few samples. Moreover, if a class of distributions has such a compression scheme, then so do the classes of products and mixtures of those distributions. The core of our main result is showing that the class of Gaussians in R^d has an efficient sample compression.

Cite

Text

Ashtiani et al. "Nearly Tight Sample Complexity Bounds for Learning Mixtures of Gaussians via Sample Compression Schemes." Neural Information Processing Systems, 2018.

Markdown

[Ashtiani et al. "Nearly Tight Sample Complexity Bounds for Learning Mixtures of Gaussians via Sample Compression Schemes." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/ashtiani2018neurips-nearly/)

BibTeX

@inproceedings{ashtiani2018neurips-nearly,
  title     = {{Nearly Tight Sample Complexity Bounds for Learning Mixtures of Gaussians via Sample Compression Schemes}},
  author    = {Ashtiani, Hassan and Ben-David, Shai and Harvey, Nicholas and Liaw, Christopher and Mehrabian, Abbas and Plan, Yaniv},
  booktitle = {Neural Information Processing Systems},
  year      = {2018},
  pages     = {3412-3421},
  url       = {https://mlanthology.org/neurips/2018/ashtiani2018neurips-nearly/}
}