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

Author:
Andrew L. Rukhin

Journal:
Proc. Amer. Math. Soc. **119** (1993), 1307-1314

MSC:
Primary 62C05; Secondary 62F11, 62F15, 62F35

DOI:
https://doi.org/10.1090/S0002-9939-1993-1166361-X

MathSciNet review:
1166361

Full-text PDF

Abstract | References | Similar Articles | Additional Information

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.

**[1]**R. Bellman,*Introduction to matrix analysis*, 2nd ed., McGraw-Hill, New York, 1970. MR**0258847 (41:3493)****[2]**M. Ben-Bassat and J. Raviv,*Renyi's entropy and the probability of error*, IEEE Trans. Inform. Theory**IT-24**(1978), 324-331. MR**0484747 (58:4626)****[3]**A. Berman and R. J. Plemmons,*Nonngative matrices in the mathematical sciences*, Academic Press, New York, 1979. MR**544666 (82b:15013)****[4]**J. T. Chu and J. C. Chueh,*Inequalities between information measures and error probability*, J. Franklin Inst.**282**(1966), 121-125. MR**0199043 (33:7193)****[5]**T. M. Cover, M. A. Freedman, and M. E. Hellman,*Optimal finite memory learning algorithms for the finite sample problem*, Information and Control**30**(1976), 49-85. MR**0405927 (53:9719)****[6]**R. G. Gallager,*Information theory and reliable communication*, Wiley, New York, 1968.**[7]**M. E. Hellman and T. M. Cover,*Learning with finite memory*, Ann. Math. Statist.**41**(1970), 765-782. MR**0272100 (42:6981)****[8]**A. Renyi,*On some problems of statistics from the point of view of information theory*, Proceedings of the Colloquium on Information Theory (Debrecen, 1969), Bolyai Janos Matematikai Tarsulat, Bolyai Math. Soc. MR**0246424 (39:7728)****[9]**I. Vajda,*Theory of statistical inference and information*, Kluwer, Dordrecht, 1989.

Retrieve articles in *Proceedings of the American Mathematical Society*
with MSC:
62C05,
62F11,
62F15,
62F35

Retrieve articles in all journals with MSC: 62C05, 62F11, 62F15, 62F35

Additional Information

DOI:
https://doi.org/10.1090/S0002-9939-1993-1166361-X

Keywords:
Classification problem,
error probability,
likelihood ratios,
linear programming,
M-matrix

Article copyright:
© Copyright 1993
American Mathematical Society