Dynamic Trees: A Structured Variational Method Giving Efficient Propagation Rules

by   Amos J. Storkey, et al.

Dynamic trees are mixtures of tree structured belief networks. They solve some of the problems of fixed tree networks at the cost of making exact inference intractable. For this reason approximate methods such as sampling or mean field approaches have been used. However, mean field approximations assume a factorized distribution over node states. Such a distribution seems unlickely in the posterior, as nodes are highly correlated in the prior. Here a structured variational approach is used, where the posterior distribution over the non-evidential nodes is itself approximated by a dynamic tree. It turns out that this form can be used tractably and efficiently. The result is a set of update rules which can propagate information through the network to obtain both a full variational approximation, and the relevant marginals. The progagtion rules are more efficient than the mean field approach and give noticeable quantitative and qualitative improvement in the inference. The marginals calculated give better approximations to the posterior than loopy propagation on a small toy problem.



There are no comments yet.


page 1

page 2

page 3

page 4


Variational Approximations between Mean Field Theory and the Junction Tree Algorithm

Recently, variational approximations such as the mean field approximatio...

Negative Tree Reweighted Belief Propagation

We introduce a new class of lower bounds on the log partition function o...

MaxEntropy Pursuit Variational Inference

One of the core problems in variational inference is a choice of approxi...

Comparative Study for Inference of Hidden Classes in Stochastic Block Models

Inference of hidden classes in stochastic block model is a classical pro...

Factored expectation propagation for input-output FHMM models in systems biology

We consider the problem of joint modelling of metabolic signals and gene...

Mixture Approximations to Bayesian Networks

Structure and parameters in a Bayesian network uniquely specify the prob...

Factored Filtering of Continuous-Time Systems

We consider filtering for a continuous-time, or asynchronous, stochastic...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.