Sum-Product Networks: A New Deep Architecture

02/14/2012
by   Hoifung Poon, et al.
0

The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sum-product networks (SPNs). SPNs are directed acyclic graphs with variables as leaves, sums and products as internal nodes, and weighted edges. We show that if an SPN is complete and consistent it represents the partition function and all marginals of some graphical model, and give semantics to its nodes. Essentially all tractable graphical models can be cast as SPNs, but SPNs are also strictly more general. We then propose learning algorithms for SPNs, based on backpropagation and EM. Experiments show that inference and learning with SPNs can be both faster and more accurate than with standard deep networks. For example, SPNs perform image completion better than state-of-the-art deep networks for this task. SPNs also have intriguing potential connections to the architecture of the cortex.

READ FULL TEXT
research
08/21/2017

Sum-Product Graphical Models

This paper introduces a new probabilistic architecture called Sum-Produc...
research
04/02/2020

Sum-product networks: A survey

A sum-product network (SPN) is a probabilistic model, based on a rooted ...
research
10/12/2017

Sum-Product-Quotient Networks

We present a novel tractable generative model that extends Sum-Product N...
research
10/22/2020

Factor Graph Grammars

We propose the use of hyperedge replacement graph grammars for factor gr...
research
10/26/2020

Stochastic Discrete Clenshaw-Curtis Quadrature

The partition function is fundamental for probabilistic graphical models...
research
08/09/2014

Approximate inference on planar graphs using Loop Calculus and Belief Propagation

We introduce novel results for approximate inference on planar graphical...
research
12/20/2019

Sum-Product Network Decompilation

There exists a dichotomy between classical probabilistic graphical model...

Please sign up or login with your details

Forgot password? Click here to reset