On Improving the Efficiency of the Iterative Proportional Fitting Procedure
نویسندگان
چکیده
Iterative proportional fitting (IPF) on junction trees is an important tool for learning in graphical models. We identify the propagation and IPF updates on the junction tree as fixed point equations of a single constrained entropy maximization problem. This allows a more efficient message updating protocol than the well known effective IPF of Jiroušek and Přeučil (1995). When the junction tree has an intractably large maximum clique size we propose to maximize an approximate constrained entropy based on region graphs (Yedidia et al., 2002). To maximize the new objective we propose a “loopy” version of IPF. We show that this yields accurate estimates of the weights of undirected graphical models in a simple experiment.
منابع مشابه
Design of Iterative Proportional Fitting Procedure for Possibility Distributions
We design an iterative proportional fitting procedure (parameterized by a continuous t-norm) for computation of multidimensional possibility distributions from its marginals, and discuss its basic properties.
متن کاملOn the Iterative Proportional Fitting Procedure: Structure of Accumulation Points and L1-error Analysis
متن کامل
Probability Measures with given Marginals and Conditionals: I-projections and Conditional Iterative Proportional Fitting
The iterative proportional fitting procedure (IPF-P) is an algorithm to compute approximately probability measures with prescribed marginals. We propose two extensions of the IPF-P, called conditional iterative proportional fitting procedures (CIPF-P), so that, additionally, given conditional distributions are taken into account. This modification is carried out by using the geometrical interpr...
متن کاملModifying Bayesian Networks by Probability Constraints
This paper deals with the following problem: modify a Bayesian network to satisfy a given set of probability constraints by only change its conditional probability tables, and the probability distribution of the resulting network should be as close as possible to that of the original network. We propose to solve this problem by extending IPFP (iterative proportional fitting procedure) to probab...
متن کاملPutting Iterative Proportional Fitting on the Researcher’s Desk
...................................................................................................................................ii
متن کامل