Optimal measures and Markov transition kernels
Article
Belavkin, R. 2013. Optimal measures and Markov transition kernels. Journal of Global Optimization. 55 (2), pp. 387-416. https://doi.org/10.1007/s10898-012-9851-1
Type | Article |
---|---|
Title | Optimal measures and Markov transition kernels |
Authors | Belavkin, R. |
Abstract | We study optimal solutions to an abstract optimization problem for measures, which is a generalization of classical variational problems in information theory and statistical physics. In the classical problems, information and relative entropy are defined using the Kullback-Leibler divergence, and for this reason optimal measures belong to a one-parameter exponential family. Measures within such a family have the property of mutual absolute continuity. Here we show that this property characterizes other families of optimal positive measures if a functional representing information has a strictly convex dual. Mutual absolute continuity of optimal probability measures allows us to strictly separate deterministic and non-deterministic Markov transition kernels, which play an important role in theories of decisions, estimation, control, communication and computation. We show that deterministic transitions are strictly sub-optimal, unless information resource with a strictly convex dual is unconstrained. For illustration, we construct an example where, unlike non-deterministic, any deterministic kernel either has negatively infinite expected utility (unbounded expected error) or communicates infinite information. |
Keywords | Expected utility; Information distance; Optimal policy; Radon measure; Randomized algorithm |
Sustainable Development Goals | 9 Industry, innovation and infrastructure |
Middlesex University Theme | Sustainability |
Research Group | Artificial Intelligence group |
Publisher | Springer |
Journal | Journal of Global Optimization |
ISSN | 0925-5001 |
Electronic | 1573-2916 |
Publication dates | |
Online | 08 Feb 2012 |
Feb 2013 | |
Publication process dates | |
Deposited | 01 Mar 2012 |
Accepted | 14 Jan 2012 |
Submitted | 01 Dec 2010 |
Output status | Published |
Copyright Statement | The final publication is available at www.springerlink.com: http://dx.doi.org/10.1007/s10898-012-9851-1 |
Digital Object Identifier (DOI) | https://doi.org/10.1007/s10898-012-9851-1 |
Scopus EID | 2-s2.0-84878576380 |
Web of Science identifier | WOS:000314278100011 |
Language | English |
File |
https://repository.mdx.ac.uk/item/8389w
Download files
70
total views14
total downloads1
views this month0
downloads this month