Information trajectory of optimal learning.
Belavkin, Roman V. ORCID: https://orcid.org/0000-0002-2356-1447
(2010)
Information trajectory of optimal learning.
In:
Dynamics of information systems: theory and applications.
Hirsch, Michael J., Pardalos, Panos M. and Murphey, Robert, eds.
Springer Optimization and Its Applications
(40)
.
Springer, pp. 29-44.
ISBN 9781441956880.
[Book Section]
Abstract
The paper outlines some basic principles of a geometric and
non-asymptotic theory of learning systems. An evolution of such a system is represented by points on a statistical manifold, and a topology related to information dynamics is introduced to define trajectories continuous in information. It is shown that optimization of learning with respect to a given utility function leads to an evolution described by a continuous trajectory. Path integrals along the trajectory define the optimal utility and information bounds. Closed form expressions are derived for two important types of utility functions. The presented approach is a generalization of the use of Orlicz spaces in information geometry, and it gives a new, geometric interpretation of the classical information value theory and statistical mechanics. In addition, theoretical predictions are evaluated experimentally by comparing performance of agents learning in a non-stationary stochastic environment.
Item Type: | Book Section |
---|---|
Research Areas: | A. > School of Science and Technology > Computer Science A. > School of Science and Technology > Computer Science > Artificial Intelligence group |
Item ID: | 3490 |
Useful Links: | |
Depositing User: | Dr Roman Belavkin |
Date Deposited: | 24 Mar 2010 13:40 |
Last Modified: | 13 Oct 2016 14:16 |
URI: | https://eprints.mdx.ac.uk/id/eprint/3490 |
Actions (login required)
![]() |
View Item |
Statistics
Additional statistics are available via IRStats2.