Error exponents for composite hypothesis testing of Markov forest distributions

The problem of composite binary hypothesis testing of Markov forest (or tree) distributions is considered. The worst-case type-II error exponent is derived under the Neyman-Pearson formulation. Under simple null hypothesis, the error exponent is derived in closed-form and is characterized in terms of the so-called bottleneck edge of the forest distribution. The least favorable distribution for detection is shown to be Markov on the second-best max-weight spanning tree with mutual information edge weights. A necessary and sufficient condition to have positive error exponent is derived.

[1]  Vincent Y. F. Tan,et al.  Learning High-Dimensional Markov Forest Distributions: Analysis of Error Rates , 2010, J. Mach. Learn. Res..

[2]  Imre Csiszár,et al.  Information Theory and Statistics: A Tutorial , 2004, Found. Trends Commun. Inf. Theory.

[3]  Thomas H. Cormen,et al.  Introduction to algorithms [2nd ed.] , 2001 .

[4]  Vincent Y. F. Tan,et al.  Learning Gaussian Tree Models: Analysis of Error Exponents and Extremal Structures , 2009, IEEE Transactions on Signal Processing.

[5]  W. Hoeffding.  Asymptotically Optimal Tests for Multinomial Distributions , 1965 .

[6]  Alan Willsky,et al.  Learning Graphical Models for Hypothesis Testing , 2007, 2007 IEEE/SP 14th Workshop on Statistical Signal Processing.

[7]  Ronald L. Rivest,et al.  Introduction to Algorithms , 1990 .

[8]  Lang Tong,et al.  A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures , 2009, IEEE Transactions on Information Theory.

[9]  Michael I. Jordan.  Graphical Models , 1998 .

[10]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[11]  Stephen E. Fienberg,et al.  Testing Statistical Hypotheses , 2005 .

[12]  Ofer Zeitouni,et al.  On universal hypotheses testing via large deviations , 1991, IEEE Trans. Inf. Theory.

[13]  Lang Tong,et al.  Detection error exponent for spatially dependent samples in random networks , 2009, 2009 IEEE International Symposium on Information Theory.

[14]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[15]  Neri Merhav,et al.  When is the generalized likelihood ratio test optimal? , 1992, IEEE Trans. Inf. Theory.