WHEN DOES A MIXTURE OF PRODUCTS CONTAIN A PRODUCT OF MIXTURES?
Skip to main content
eScholarship
Open Access Publications from the University of California

UCLA

UCLA Previously Published Works bannerUCLA

WHEN DOES A MIXTURE OF PRODUCTS CONTAIN A PRODUCT OF MIXTURES?

  • Author(s): Montufar, Guido F
  • Morton, Jason
  • et al.

Published Web Location

https://epubs.siam.org/doi/10.1137/140957081?mobileUi=0
No data is associated with this publication.
Abstract

We derive relations between theoretical properties of restricted Boltzmann machines (RBMs), popular machine learning models which form the building blocks of deep learning models, and several natural notions from discrete mathematics and convex geometry. We give implications and equivalences relating RBM-representable probability distributions, perfectly reconstructible inputs, Hamming modes, zonotopes and zonosets, point configurations in hyperplane arrangements, linear threshold codes, and multi-covering numbers of hypercubes. As a motivating application, we prove results on the relative representational power of mixtures of product distributions and products of mixtures of pairs of product distributions (RBMs) that formally justify widely held intuitions about distributed representations. In particular, we show that a mixture of products requiring an exponentially larger number of parameters is needed to represent the probability distributions which can be obtained as products of mixtures.

Many UC-authored scholarly publications are freely available on this site because of the UC's open access policies. Let us know how this access is important for you.

Item not freely available? Link broken?
Report a problem accessing this item