file.pdf (262 kB)

PAC Learning Axis-Aligned Mixtures of Gaussians with No Separation Assumption

Download (262 kB)
journal contribution
posted on 01.01.2013 by Jon Feldman, Rocco A. Servedio, Ryan O'Donnell
We propose and analyze a new vantage point for the learning of mixtures of Gaussians: namely, the PAC-style model of learning probability distributions introduced by Kearns et al. [13]. Here the task is to construct a hypothesis mixture of Gaussians that is statistically indistinguishable from the actual mixture generating the data; specifically, the KL divergence should be at most ε. In this scenario, we give a poly(n/ε) time algorithm that learns the class of mixtures of any constant number of axis-aligned Gaussians in Rn. Our algorithm makes no assumptions about the separation between the means of the Gaussians, nor does it have any dependence on the minimum mixing weight. This is in contrast to learning results known in the “clustering” model, where such assumptions are unavoidable. Our algorithm relies on the method of moments, and a subalgorithm developed in [9] for a discrete mixture-learning problem.

History

Publisher Statement

Copyright: © 2013 Goode A. This is an open‑access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Date

01/01/2013

Licence

Exports

Licence

Exports