Information Geometry and Information Theory in Machine Learning
Part of the
Lecture Notes in Computer Science
book series (LNCS, volume 4985)
Information geometry is a general framework of Riemannian manifolds with dual affine connections. Some manifolds (e.g. the manifold of an exponential family) have natural connections (e.g. e- and m-connections) with which the manifold is dually-flat. Conversely, a dually-flat structure can be introduced into a manifold from a potential function. This paper shows the case of quasi-additive algorithms as an example.
Information theory is another important tool in machine learning. Many of its applications consider information-theoretic quantities such as the entropy and the mutual information, but few fully recognize the underlying essence of them. The asymptotic equipartition property is one of the essence in information theory.
This paper gives an example of the property in a Markov decision process and shows how it is related to return maximization in reinforcement learning.
KeywordsRiemannian Manifold Reinforcement Learning Independent Component Analysis Exponential Family Markov Chain Model
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Amari, S.I.: Differential-Geometrical Methods in Statistics. Lecture Notes in Statistics, vol. 28. Springer, Heidelberg (1985)zbMATHGoogle Scholar
Amari, S.I., Nagaoka, H.: Methods of Information Geometry. Translations of Mathematical Monographs, vol. 191. AMS and Oxford Univ. Press, Oxford (2000)zbMATHGoogle Scholar
Cover, T.M., Thomas, J.A.: Elements of Information Theory, 2nd edn. John Wiley and Sons, Inc., Hoboken (2006)zbMATHGoogle Scholar
Grove, A.J., Littlestone, N., Schuurmans, D.: General convergence results for linear discriminant updates. Machine Learning 43(3), 173–210 (2001)zbMATHCrossRefGoogle Scholar
Ikeda, K.: Geometric properties of quasi-additive learning algorithms. IEICE Trans. Fundamentals E89-A(10), 2812–2817 (2006)CrossRefGoogle Scholar
Suzuki, J.: A markov chain analysis on simple genetic algorithms. IEEE Trans. on Systems, Man and Cybernetics 25(4), 655–659 (1995)CrossRefGoogle Scholar
Suzuki, J.: A further result on the markov chain model of genetic algorithms and its application to a simulated annealing-like strategy. IEEE Trans. on Systems, Man and Cybernetics, Part B, Cybernetics 28(1), 95–102 (1998)CrossRefGoogle Scholar
Iwata, K., Ikeda, K., Sakai, H.: The asymptotic equipartition property in reinforcement learning and its relation to return maximization. Neural Networks 19(1), 62–75 (2006)zbMATHCrossRefGoogle Scholar
Iwata, K., Ikeda, K., Sakai, H.: A statistical property of multi-agent learning based on Markov decision process. IEEE Trans. on Neural Networks 17(4), 829–842 (2006)CrossRefGoogle Scholar
© Springer-Verlag Berlin Heidelberg 2008