Lower bound on the error probability for families with bounded likelihood ratios

Rukhin, Andrew L.

doi:10.1090/S0002-9939-1993-1166361-X

Lower bound on the error probability for families with bounded likelihood ratios
HTML articles powered by AMS MathViewer

by Andrew L. Rukhin PDF

Proc. Amer. Math. Soc. 119 (1993), 1307-1314 Request permission

Abstract:

In the classification problem a new sharp lower bound for the error probability is derived. This bound depends only on the prior probabilities and on the support of pairwise likelihood ratios.

References

Richard Bellman, Introduction to matrix analysis, 2nd ed., McGraw-Hill Book Co., New York-Düsseldorf-London, 1970 (Russian). MR 0258847
Moshe Ben-Bassat and Josef Raviv, Rényi’s entropy and the probability of error, IEEE Trans. Inform. Theory IT-24 (1978), no. 3, 324–331. MR 484747, DOI 10.1109/tit.1978.1055890
Abraham Berman and Robert J. Plemmons, Nonnegative matrices in the mathematical sciences, Computer Science and Applied Mathematics, Academic Press [Harcourt Brace Jovanovich, Publishers], New York-London, 1979. MR 544666
J. T. Chu and J. D. Chueh, Inequalities between information measures and error probability, J. Franklin Inst. 282 (1966), 121–125. MR 199043, DOI 10.1016/0016-0032(66)90359-0
Thomas M. Cover, Michael A. Freedman, and Martin E. Hellman, Optimal finite memory learning algorithms for the finite sample problem, Information and Control 30 (1976), no. 1, 49–85. MR 405927

Information theory and reliable communication

Martin E. Hellman and Thomas M. Cover, Learning with finite memory, Ann. Math. Statist. 41 (1970), 765–782. MR 272100, DOI 10.1214/aoms/1177696958
A. Rényi, On some problems of statistics from the point of view of information theory, Proc. Colloquium on Information Theory (Debrecen, 1967) János Bolyai Math. Soc., Budapest, 1968, pp. 343–357. MR 0246424

Theory of statistical inference and information