Learning Mixtures of Gaussians with Maximum-a-Posteriori Oracle

Abstract

We consider the problem of estimating the parameters of a mixture of distributions, where each component distribution is from a given parametric family e.g. exponential, Gaussian etc. We define a learning model in which the learner has access to a “maximum-a-posteriori” oracle which given any sample from a mixture of distributions, tells the learner which component distribution was the most likely to have generated it. We describe a learning algorithm in this setting which accurately estimates the parameters of a mixture of $k$ spherical Gaussians in $\mathbb{R}^d$ assuming the component Gaussians satisfy a mild separation condition. Our algorithm uses only polynomially many (in $d, k$) samples and oracle calls, and our separation condition is much weaker than those required by unsupervised learning algorithms like [Arora 01, Vempala 02].

Cite

Text

Mahalanabis. "Learning Mixtures of Gaussians with Maximum-a-Posteriori Oracle." Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011.

Markdown

[Mahalanabis. "Learning Mixtures of Gaussians with Maximum-a-Posteriori Oracle." Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011.](https://mlanthology.org/aistats/2011/mahalanabis2011aistats-learning/)

BibTeX

@inproceedings{mahalanabis2011aistats-learning,
  title     = {{Learning Mixtures of Gaussians with Maximum-a-Posteriori Oracle}},
  author    = {Mahalanabis, Satyaki},
  booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics},
  year      = {2011},
  pages     = {489-497},
  volume    = {15},
  url       = {https://mlanthology.org/aistats/2011/mahalanabis2011aistats-learning/}
}