Abstract
We consider the problem of finding the maximum values of divergences D(P‖Q) and D(Q‖P) for probability distributions P and Q ranging in the finite set \(\mathcal{N}=\left\{1,\;2,...,n\right\}\) provided that both the variation distance V (P,Q) between them and either the probability distribution Q or (in the case of D(P‖Q)) only the value of the minimal component q min of the probability distribution Q are given. Precise expressions for the maximum values of these divergences are obtained. In several cases these expressions allow us to write out some explicit formulas and simple upper and lower bounds for them. Moreover, explicit formulas for the maximum of D(P‖Q) for given V (P,Q) and q min and also for the maximum of D(Q‖P) for given Q and V (P,Q) are obtained for all possible values of these parameters.
Similar content being viewed by others
References
Fedotov, A.A., Harremöes, P., and Topsøe, F., Refinements of Pinsker’s Inequality, IEEE Trans. Inform. Theory, 2003, vol. 49, no. 6, pp. 1491–1498.
Csiszár, I. and Körner, J., Information Theory: Coding Theorems for Discrete Memoryless Systems, New York: Academic; Budapest: Akad. Kiad´o, 1981. Translated under the title Teoriya informatsii: teoremy kodirovaniya dlya diskretnykh sistem bez pamyati, Moscow: Mir, 1985.
Vajda, I., Note on Discrimination Information and Variation, IEEE Trans. Inform. Theory, 1970, vol. 16, no. 6, pp. 771–773.
Ordentlich, E. and Weinberger, M.J., A Distribution Dependent Refinement of Pinsker’s Inequality, IEEE Trans. Inform. Theory, 2005, vol. 51, no. 5, pp. 1836–1840.
Prelov, V.V., On Coupling of Probability Distributions and Estimating the Divergence through Variation, Probl. Peredachi Inf., 2017, vol. 53, no. 3, pp. 16–22 [Probl. Inf. Transm. (Engl. Transl.), 2017, vol. 53, no. 3, pp. 215–221].
Csiszár, I. and Talata, Z., Context Tree Estimation for Not Necessarily Finite Memory Processes via BIC and MDL, IEEE Trans. Inform. Theory, 2006, vol. 52, no. 3, pp. 1007–1016.
Sason, I. and Verdú, S., Upper Bounds on the Relative Entropy and Rényi Divergence as a Function of Total Variation Distance for Finite Alphabets, in Proc. 2015 IEEE Information Theory Workshop (ITW’2015), Jeju, Korea, Oct. 11–15, 2015, pp. 214–218.
Sason, I. and Verdú, S., f-Divergence Inequalities, IEEE Trans. Inform. Theory, 2016, vol. 62, no. 11, pp. 5973–6006.
Funding
Funding The research was supported in part by the Russian Foundation for Basic Research, project no. 19-01-00364.
Author information
Authors and Affiliations
Corresponding author
Additional information
Russian Text © The Author(s), 2019, published in Problemy Peredachi Informatsii, 2019, Vol. 55, No. 3, pp. 21–29.
Rights and permissions
About this article
Cite this article
Prelov, V.V. Optimal Upper Bounds for the Divergence of Finite-Dimensional Distributions under a Given Variational Distance. Probl Inf Transm 55, 218–225 (2019). https://doi.org/10.1134/S0032946019030025
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0032946019030025