Abstract
In this paper, we consider the Bayesian multiple hypothesis testing problem from the stance of computational geometry. We first recall that the probability of error of the optimal decision rule, the maximum a posteriori probability (MAP) criterion, is related to both the total variation and the Chernoff statistical distances. We then consider the exponential family manifolds, and show that the MAP rule amounts to a nearest neighbor classifier that can be implemented either by point locations in an additive Bregman Voronoi diagram or by nearest neighbor queries using various techniques of computational geometry. Finally, we show that computing the best error exponent upper bounding the probability of error, the Chernoff distance, amounts to (1) find a unique geodesic/bisector intersection point for binary hypothesis, (2) solve a closest Bregman pair problem for multiple hypothesis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Leang, C.C., Johnson, D.H.: On the asymptotics of M-hypothesis Bayesian detection. IEEE Transactions on Information Theory 43(1), 280–282 (1997)
Hellman, M.E., Raviv, J.: Probability of error, equivocation and the Chernoff bound. IEEE Transactions on Information Theory 16, 368–372 (1970)
Chernoff, H.: A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Annals of Mathematical Statistics 23, 493–507 (1952)
Brown, L.D.: Fundamentals of statistical exponential families: with applications in statistical decision theory. Institute of Mathematical Statistics, Hayworth (1986)
Amari, S., Nagaoka, H.: Methods of Information Geometry. Oxford University Press (2000)
Banerjee, A., Merugu, S., Dhillon, I.S., Ghosh, J.: Clustering with Bregman divergences. Journal of Machine Learning Research 6, 1705–1749 (2005)
Westover, M.: Asymptotic geometry of multiple hypothesis testing. IEEE Transactions on Information Theory 54(7), 3327–3329 (2008)
Boissonnat, J.D., Nielsen, F., Nock, R.: Bregman Voronoi diagrams. Discrete & Computational Geometry 44(2), 281–307 (2010)
Boissonnat, J.D., Yvinec, M.: Algorithmic Geometry. Cambridge University Press, New York (1998)
Nielsen, F.: k-MLE: A fast algorithm for learning statistical mixture models. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). IEEE (2012); preliminary, technical report on arXiv
Piro, P., Nielsen, F., Barlaud, M.: Tailored Bregman ball trees for effective nearest neighbors. In: European Workshop on Computational Geometry (EuroCG), LORIA, Nancy, France. IEEE (March 2009)
Nielsen, F., Piro, P., Barlaud, M.: Bregman vantage point trees for efficient nearest neighbor queries. In: Proceedings of the 2009 IEEE International Conference on Multimedia and Expo (ICME), pp. 878–881 (2009)
Garcia, V., Debreuve, E., Nielsen, F., Barlaud, M.: k-nearest neighbor search: Fast GPU-based implementations and application to high-dimensional feature matching. In: IEEE International Conference on Image Processing (ICIP), pp. 3757–3760 (2010)
Nielsen, F.: An information-geometric characterization of Chernoff information. IEEE Signal Processing Letters (SPL) 20(3), 269–272 (2013)
Nielsen, F., Boltz, S.: The Burbea-Rao and Bhattacharyya centroids. IEEE Transactions on Information Theory 57(8), 5455–5466 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nielsen, F. (2013). Hypothesis Testing, Information Divergence and Computational Geometry. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2013. Lecture Notes in Computer Science, vol 8085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40020-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-40020-9_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40019-3
Online ISBN: 978-3-642-40020-9
eBook Packages: Computer ScienceComputer Science (R0)