The paper outlines some basic principles of geometric and nonasymptotic 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 nonstationary stochastic environment.
CITATION STYLE
Belavkin, R. V. (2010). Information trajectory of optimal learning. Springer Optimization and Its Applications, 40, 29–44. https://doi.org/10.1007/978-1-4419-5689-7_2
Mendeley helps you to discover research relevant for your work.