Computer Science – Information Theory
Scientific paper
2005-06-05
Computer Science
Information Theory
13 pages; accepted for publication in the IEEE Transactions on Information Theory
Scientific paper
A broad set of sufficient conditions that guarantees the existence of the maximum entropy (maxent) distribution consistent with specified bounds on certain generalized moments is derived. Most results in the literature are either focused on the minimum cross-entropy distribution or apply only to distributions with a bounded-volume support or address only equality constraints. The results of this work hold for general moment inequality constraints for probability distributions with possibly unbounded support, and the technical conditions are explicitly on the underlying generalized moment functions. An analytical characterization of the maxent distribution is also derived using results from the theory of constrained optimization in infinite-dimensional normed linear spaces. Several auxiliary results of independent interest pertaining to certain properties of convex coercive functions are also presented.
Ishwar Prakash
Moulin Pierre
No associations
LandOfFree
On the existence and characterization of the maxent distribution under general moment inequality constraints does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with On the existence and characterization of the maxent distribution under general moment inequality constraints, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On the existence and characterization of the maxent distribution under general moment inequality constraints will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-202058