Sample-efficient strategies for learning in the presence of noise

Journal of the ACM

Volumn 46, Issue 5, 1999, Pages 684-719

  Cesa Bianchi, Nicolö ^b,d   Dichterman, Eli ^c,e   Fischer, Paul ^a,b   Shamir, Eli ^c,e   Simon, Hans Ulrich ^a,d   Dichterman, E ^a,b   Shamir, E ^c,e   Ulrich Simon, H ^c,d  

^a UNIVERSITY OF MILAN   (Italy)

^b IBM HAIFA RESEARCH LAB   (Israel)

^c TU DORTMUND UNIVERSITY   (Germany)

^d HEBREW UNIVERSITY OF JERUSALEM   (Israel)

^e RUHR UNIVERSITY BOCHUM   (Germany)

Author keywords

Learning with malicious noise; Pac learning

Indexed keywords

ACOUSTIC NOISE; ERROR ANALYSIS; FUNCTIONS; PROBABILITY; SAMPLING; STRATEGIC PLANNING;

LEARNING WITH MALICIOUS NOISE; NOISE RATES; PAC LEARNING; SAMPLE SIZE;

LEARNING SYSTEMS;

EID: 0010572906     PISSN: 00045411     EISSN: None     Source Type: Journal    
DOI: 10.1145/324133.324221     Document Type: Article

References (18)

1. BAHADUR, R. 1960. Some approximations to the binomial distribution function. Ann. Math. Stat. 31, 43-54.
2. BAHADUR, R., RANGA-RAO, R. 1960. On deviations of the sample mean. Ann. Math. Stat. 31, 1015-1027.
3. BLUMER, A., EHRENFEUCHT, A., HAUSSLER, D., WARMUTH, M. K. 1989. Learnability and the Vapnik-Chervonenkis dimension.J. ACM36, 4, (Oct.), 929-965.
4. CHOW, Y. S., TEICHER, H. 1988. Probability Theory. Springer-Verlag, New York.
5. EHRENFEUCHT, A., HAUSSLER, D., KEARNS, M., VALIANT, L. 1989. A general lower bound on the number of examples needed for learning. Inf. Comput. 82, 3, 247-261.
6. GENTILE, C., HELMBOLD, D. 1998. Improved lower bounds for learning from noisy examples: An information-theoretic approach. In Proceedings of the llth Workshop on Computational Learning Theory (CoLT '98) (Madison, Wise., July 24-26). ACM, New York, pp. 104-115.
7. JOGDEO, K., SAMUELS, S. M. 1968. Monotone convergence of binomial probabilities and a generalization of ramanujan's equation. Ann. Math. Sta. 39, 4, 1191-1195.
8. KEARNS, M., Li, M. 1993. Learning in the presence of malicious errors. SIAM J. Comput. 22, 807-837.
9. KEARNS, M. J., SCHAPIRE, R. E. 1994. Efficient distribution-free learning of probabilistic concepts. J. Comput. Syst. Sei. 48, 3, 464-497.
10. KEARNS, M. J., SCHAPIRE, R. E., SELLIE, L. M. 1994. Toward efficient agnostic learning. Mach. Learn. 17, 2/3, 115-142.
11. LAIRD, P. D. 1988. Learning from good and bad data. In Kluwer International Series in Engineering and Computer Science. Kluwer Academic Publishers, Boston, Mass.
12. LITTLEWOOD, J. 1969. On the probability in the tail of a binomial distribution. Adv. Appl. Prob, 1, 43-72.
13. SAUER, N. 1972. On the density of families of sets. J. Combin. Th. A 13, 145-147.
14. SHELAH, S. 1972. A combinatorial problem; Stability and order for models and theories in infinitary languages. Pacific J. Math. 41, 247-261.
15. SIMON, H. U. 1996a. General bounds on the number of examples needed for learning probabilistic concepts. J. Comput. Syst. Sei. 52, 2, 239-255.
16. SIMON, H. U. 1996b. A general upper bound on the number of examples sufficient to learn in the presence of classification noise. Unpublished Manuscript.
17. VALIANT, L. G. 1984. A theory of the learnable. Commun. ACM 27, 11 (Nov.), 1134-1142.
18. VAPNIK, V. 1982. Estimation of Dependences Based on Empirical Data. Springer-Verlag, New York.