The Community for Technology Leaders
RSS Icon
Subscribe
Pittsburgh, Pennsylvania, USA
Oct. 23, 2005 to Oct. 25, 2005
ISBN: 0-7695-2468-0
pp: 501-510
Jon Feldman , Columbia University
Ryan ODonnell , Microsoft Research
Rocco A. Servedio , Dept. of Computer Science, Columbia University
ABSTRACT
<p>We consider the problem of learning mixtures of product distributions over discrete domains in the distribution learning framework introduced by Kearns et al. [19]. We give a poly (n/ \in ) time algorithm for learning a mixture of k arbitrary product distributions over the n-dimensional Boolean cube {0,1}^n to accuracy , for any constant k. Previous poly(n)-time algorithms could only achieve this for k = 2 product distributions; our result answers an open question stated independently in [8] and [15]. We further give evidence that no polynomial time algorithm can succeed when k is superconstant, by reduction from a notorious open problem in PAC learning. Finally, we generalize our poly(n/ \in) time algorithm to learn any mixture of k = O(1) product distributions over {0, 1, . . . , b}^n, for any b = O(1).</p>
INDEX TERMS
null
CITATION
Jon Feldman, Ryan ODonnell, Rocco A. Servedio, "Learning mixtures of product distributions over discrete domains", FOCS, 2005, 2013 IEEE 54th Annual Symposium on Foundations of Computer Science, 2013 IEEE 54th Annual Symposium on Foundations of Computer Science 2005, pp. 501-510, doi:10.1109/SFCS.2005.46
21 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool