Discriminative Learning of Sum-Product Networks

7 years 9 months ago
Discriminative Learning of Sum-Product Networks
Sum-product networks are a new deep architecture that can perform fast, exact inference on high-treewidth models. Only generative methods for training SPNs have been proposed to date. In this paper, we present the first discriminative training algorithms for SPNs, combining the high accuracy of the former with the representational power and tractability of the latter. We show that the class of tractable discriminative SPNs is broader than the class of tractable generative ones, and propose an efficient backpropagation-style algorithm for computing the gradient of the conditional log likelihood. Standard gradient descent suffers from the diffusion problem, but networks with many layers can be learned reliably using “hard” gradient descent, where marginal inference is replaced by MPE inference (i.e., inferring the most probable state of the non-evidence variables). The resulting updates have a simple and intuitive form. We test discriminative SPNs on standard image classi...
Robert Gens and Pedro Domingos
Added 28 Dec 2012
Updated 28 Dec 2012
Type Conference
Year 2012
Where NIPS
Authors Robert Gens and Pedro Domingos
Comments (1)
Marr-20111226-small.jpgNIPS 2012 Best Student Paper Award


login or register to post comments