Abstract
Entropy has been widely employed as an optimization function for problems in computer vision and pattern recognition. To gain insight into such methods it is important to characterize the behavior of the maximum-entropy probability distributions that result from the entropy optimization. The aim of this paper is to establish properties of multivariate distributions maximizing entropy for a general class of entropy functions, called Rényi’s α-entropy, under a covariance constraint. First we show that these entropy-maximizing distributions exhibit interesting properties, such as spherical invariance, and have a stochastic Gaussian-Gamma mixture representation. We then turn to the question of stability of the class of entropy-maximizing distributions under addition.
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
Abramowitz, M., Stegun, I.: Handbook of mathematical functions with formulas, graphs, and mathematical tables, U.S. Govt. Print. Off. Applied Mathematics Series, vol. 55 (1964)
Chu, K.C.: Estimation and decision for linear systems with elliptical random processes. IEEE Trans. on Automatic Control 18, 499–505 (1973)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley, New York (1987)
Csiszár, I.: Information-type measures of difference of probability distributions and indirect observations. Studia Sci. Math. Hungar. 2, 299–318 (1967)
Feller, W.: An introduction to probability theory and its applications, 3rd edn., vol. I. John Wiley & Sons, Chichester (1968)
Geman, D., Jedynak, B.: An active testing model for tracking roads in satellite images. IEEE Trans. on Pattern Anal. and Machine Intell. 1, 10–17 (1996)
Gullberg, G.T., Tsui, B.M.W.: Maximum entropy reconstruction with constraints: Iterative algorithms for solving the primal and dual programs. In: de Graaf, C.N., Viergever, M.A. (eds.) Information Processing in Medical Imaging, ch. 23. Plenum Press, New York (1988)
Heemuchwala, H., Hero, A.O., Carson, P.: Image registration using entropy measures and entropic graphs. To appear in European Journal of Signal Processing, special Issue on Content-based Visual Information Retrieval (December 2003)
Hero, A.O., Ma, B., Michel, O., Gorman, J.: Applications of entropic spanning graphs. IEEE Signal Processing Magazine 19(5), 85–95 (2002)
Kapur, J.N.: Generalised Cauchy and Student’s distributions as maximumentropy distributions. Proc. Nat. Acad. Sci. India Sect. A 58(2), 235–246 (1988)
McEliece, R.J., Rodemich, E.R., Swanson, L.: An entropy maximization problem elated to optical communication. IEEE Trans. on Inform. Theory 32, 322–325 (1986)
Mendes, R.S., Tsallis, C.: Renormalization group approach to nonextensive statistical mechanics. Phys. Lett. A 285(5-6), 273–278 (2001)
Miller, M.I., Snyder, D.L.: The role of likelihood and entropy in incompletedata problems: applications to estimating point-process intensities and Toeplitz constrained covariances. In: IEEE Proceedings, 75th edn., pp. 892–907 (1987)
Moriguti, S.: A lower bound for a probability moment of any absolutely continuous distribution with finite variance. Ann. Math. Statistics 23, 286–289 (1952)
Oliveira, F.A., Mello, B.A., Xavier Jr., I.M.: Scaling transformation of random walk distributions in a lattice. Physical Review. E 61(6, Part B), 7200–7203 (2000)
Rényi, A.: On measures of entropy and information. In: Proc. 4th Berkeley Symp. Math. Stat. and Prob., vol. 1, pp. 547–561 (1961)
Silvey, S.D., Ali, S.M.: A general class of coefficients of divergence of one distribution from another. J. Roy. Statist. Soc. Ser. B 28, 131–142 (1966)
Vignat, C., Costa, J., Hero, A.: Characterization of the multivariate distributions maximazing Tsallis entropy under covariance constraint. Technical report (January 2003)
Walker, G.A., Saw, J.G.: The distribution of linear combinations of t-variables. J. Amer. Statist. Assoc. 73(364), 876–878 (1978)
Witkovsky, V.: On the exact computation of the density and of the quantiles of linear combinations of t and F random variables. J. Statist. Plann. Inference 94(1), 1–13 (2001)
Zografos, K.: On maximum entropy characterization of Pearson’s type II and VII multivariate distributions. Journal of Multivariate Analysis 71(1), 67–75 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Costa, J., Hero, A., Vignat, C. (2003). On Solutions to Multivariate Maximum α-Entropy Problems. In: Rangarajan, A., Figueiredo, M., Zerubia, J. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2003. Lecture Notes in Computer Science, vol 2683. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45063-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-45063-4_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40498-9
Online ISBN: 978-3-540-45063-4
eBook Packages: Springer Book Archive