f340f1b1f65b6df5b5e3f94d95b11daf-Reviews.html

Mixture models (MM) assume that instances are drawn from a mixture of K component distributions with unknown coefficients. Topic models (TM), on the other hand, assume that samples/documents have different mixing weights of the underlying topic distribution over words. This paper tries to close the gap between MM and TM. Their proposed model assumes that several samples are drawn from the same underlying K distributions, but similar to TM, has different mixing weights and assume that instances are treated as feature vectors similar to MM. This is a theory paper that provides two algorithms that can recover the underlying structure for this model.