Computing with Fisher geodesics and extended exponential families
- 224 Downloads
Recent progress using geometry in the design of efficient Markov chain Monte Carlo (MCMC) algorithms have shown the effectiveness of the Fisher Riemannian structure. Furthermore, the theory of the underlying geometry of spaces of statistical models has made an important breakthrough by extending the classical theory on exponential families to their closures, the so-called extended exponential families. This paper looks at the underlying geometry of the Fisher information, in particular its limiting behaviour near boundaries, which illuminates the excellent behaviour of the corresponding geometric MCMC algorithms. Further, the paper shows how Fisher geodesics in extended exponential families smoothly attach the boundaries of extended exponential families to their relative interior. We conjecture that this behaviour could be exploited for trans-dimensional MCMC algorithms.
KeywordsExtended exponential family Fisher geodesic Fisher metric Information geometry Markov chain Monte Carlo
Thanks to EPSRC for grants EP/E017878/1 and EP/L010429/1
- Anaya-Izquierdo, K., Critchley, F., Marriott, P., Vos, P.: Computational information geometry: foundations. In: Proceedings of Geometric Science of Information 2013. Lecture Notes in Computer Science, pp. 311–318. Springer, Berlin (2013).Google Scholar
- Lauritzen, S.: Graphical Models. Oxford University Press, Oxford (1996)Google Scholar
- R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2006). http://www.R-project.org. ISBN 3-900051-07-0. Accessed Feb 2014