A spectral algorithm for learning mixture models
Journal of Computer and System Sciences - Special issue on FOCS 2002
The spectral method for general mixture models
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Denials leak information: Simulatable auditing
Journal of Computer and System Sciences
Hi-index | 0.00 |
The class of logconcave functions in \mathbb{R}^n is a common generalization of Gaussians and of indicator functions of convex sets. Motivated by the problem of sampling from a logconcave density function, we study their geometry and introduce an analysis technique for "smoothing" them out. This leads to efficient sampling algorithms with no assumptions on the local smoothness of the density function. After appropriate preprocessing, both the ball walk (with a Metropolis filter) and a generalization of hit-and-run produce a point from approximately the right distribution in time 0*(n4 and in amortized time 0*(n3 if many sample points are needed (where the asterisk indicates that dependence on the error parameter and factors of log n are not shown). The bounds are optimal in terms of a "roundness" parameter and match the best-known bounds for the special case of the uniform density over a convex set.