Iterative Procedure for Obtaining I-Projections onto the Intersection of Convex Sets

摘要

A frequently occuring problem is to find that probability distribution (PD) lying within a convex set which minimizes the I-divergence between it and given PD R. This document proposes an iterative procedure which requires only that the set be convex (and not necessarily linear) which under general conditions will converge to the desired I-projection.