Timezone: »

Deep Homogeneous Mixture Models: Representation, Separation, and Approximation
Priyank Jaini · Pascal Poupart · Yaoliang Yu

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 210 #85
At their core, many unsupervised learning models provide a compact representation of homogeneous density mixtures, but their similarities and differences are not always clearly understood. In this work, we formally establish the relationships among latent tree graphical models (including special cases such as hidden Markov models and tensorial mixture models), hierarchical tensor formats and sum-product networks. Based on this connection, we then give a unified treatment of exponential separation in \emph{exact} representation size between deep mixture architectures and shallow ones. In contrast, for \emph{approximate} representation, we show that the conditional gradient algorithm can approximate any homogeneous mixture within $\epsilon$ accuracy by combining $O(1/\epsilon^2)$ ``shallow'' architectures, where the hidden constant may decrease (exponentially) with respect to the depth. Our experiments on both synthetic and real datasets confirm the benefits of depth in density estimation.

Author Information

Priyank Jaini (University of Waterloo)
Pascal Poupart (University of Waterloo & RBC Borealis AI)
Yaoliang Yu (University of Waterloo)

More from the Same Authors