Characterizations of learnability for classes of (0, …, n)-valued functions

Journal of Computer and System Sciences

Volumn 50, Issue 1, 1995, Pages 74-86

  Bendavid, Shai ^a   Cesa Bianchi, Nicolò ^b   Haussler, David ^c   Long, Philip M ^d  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b UNIVERSITY OF MILAN   (Italy)

^c UNIVERSITY OF CALIFORNIA   (United States)

^d DUKE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATION THEORY; COMPUTATIONAL COMPLEXITY; ENCODING (SYMBOLS); FUNCTIONS; GRAPH THEORY; MATHEMATICAL MODELS; SET THEORY;

BINARY FUNCTIONS; GRAPH DIMENSION; MULTIVALUED FUNCTION; NATARAJAN DIMENSION; POLLARD PSEUDO DIMENSION; VAPNIK CHERVONENKIS DIMENSION;

LEARNING SYSTEMS;

EID: 0029252255     PISSN: 00220000     EISSN: 10902724     Source Type: Journal    
DOI: 10.1006/jcss.1995.1008     Document Type: Article

References (19)

1. N. Alon. On the density of sets of vectors. Discrete Math. 24 (1983), 177-184.
2. R. P. Anstee, A forbidden configuration theorem of Alon, J. Combin. Theory Ser. A 47 (1988), 16-27.
3. P. L. Barlett, P. M. Long, and R. C. Williamson, Fat-shattering and the learnability of real-valued functions, manuscript, 1993.
4. A. Blumer, A. Ehrenfeucht. D. Haussler, and M. K. Warmuth. Learnability and the Vapnik-Chervonenkis dimension, J. Assoc. Comput. Mach. 36, No. 4 (1989). 929-965.
5. R. M. Dudley, Universal Donsker classes and metric entropy, Ann. Probab. 15. No. 4 (1987), 1306-1326.
6. A. Ehrenfeucht, D. Haussler, M. Kearns, and L. G. Valiant. A general lower bound on the number of examples needed for learning. Inform, and Comput. 82, No. 3 (1989). 247-251.
7. D. Haussler, Decision theoretic generalizations of the PAC model for neural net and other learning applications. Inform, and Comput. 100 (1992), 78-150.
8. D. Haussler and P. M. Long. “A Generalization of Sauer’s Lemma,” Technical Report UCSC-CRL-90-15, U.C. Santa Cruz, 1990.
9. M. G. Karpovsky and V. D. Milman, Coordinate density of sets of vectors. Discrete Math. 24 (1978), 177-184.
10. B. K. Natarajan, On learning sets and functions, Mach. Learning 4 (1989). 67-97.
11. B. K Natarajan, “Machine Learning: A Theoretical Approach," Morgan Kaufmann, San Mateo. CA. 1991.
12. D. Pollard, “Convergence of Stochastic Processes,” Springer-Verlag, New York/Berlin, 1984.
13. D. Pollard, “Empirical Processes: Theory and Applications, of NSF-CBMS Regional Conference Series in Probability and Statistics, Vol. 2, Institute of Math. Statist, and Am. Stat. Assoc., Alexandria. VA, 1990.
14. J. Shawe-Taylor, M. Anthony, and R. L. Biggs, "Bounding Sample Size with the Vapnik-Chervonenkis Dimension,” Technical Report CSD-TR-618, University of London, Royal Halloway and Bedford New College, 1989.
15. J. M. Steele, Existence of submatrices with all possible columns. J. Combin. Theory Ser. A 24 (1978), 84-88.
16. L. Valiant, A theory of the learnable. Comm. ACM 27, No. 11 (1984), 1134-1142.
17. V. N. Vapnik, “Estimation of Dependences Based on Empirical Data,” Springer Verlag, Berlin/New York, 1982.
18. V. N. Vapnik, Inductive principles of the search for empirical dependences, in “Proceedings, 2nd Annual Workshop on Computational Learning Theory, 1989.
19. V. N. Vapnik and A. Y. Chervonenkis, On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl. 16, No. 2 (1971), 264-280.