Published on Fri Apr 10 2015

Jian Li, Yuval Rabani, Leonard J. Schulman, Chaitanya Swamy

We study the problem of learning from unlabeled samples very generalistical mixture models on large finite sets. We give the first efficient algorithms for learning this mixture model. Our model and results have applications to a variety of unsupervised learning scenarios, including collaborative filtering.

0

0

0

We study the problem of learning from unlabeled samples very general
statistical mixture models on large finite sets. Specifically, the model to be
learned,