Scale-sensitive dimensions and skeleton estimates for classification

Discrete Applied Mathematics

Volumn 86, Issue 1, 1998, Pages 37-61

  Horváth, Márta ^a   Lugosi, Gábor ^b  

^a BUDAPEST UNIVERSITY OF TECHNOLOGY AND ECONOMICS   (Hungary)

^b UNIVERSITAT POMPEU FABRA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0346398192     PISSN: 0166218X     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0166-218X(98)00013-4     Document Type: Article

References (31)

1. N. Alon, S. Ben-David, N. Cesa-Bianchi, D. Haussler, Scale-sensitive dimensions, uniform convergence, and learnability, Technical Report 143-95, DSI, University of Milan, Italy, 1993. An extended abstract appeared in the Proc. 1993 IEEE Symposium on the Foundations of Computer Science, IEEE Press, New York.
2. M. Anthony, P.L. Bartlett, Function learning from interpolation, Technical report, Department of Systems Engineering, Research School of Information Sciences and Engineering, Australian National University, Canberra, Australia, 1994.
3. M. Anthony, J. Shawe-Taylor, A result of Vapnik with applications, Discrete Appl. Math. 47 (1993) 207-217.
4. P.L. Bartlett, The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network, IEEE Trans. Inform. Theory (1997) to appear.
5. P.L. Bartlett, S.R. Kulkarni, S.E. Posner, Covering numbers for real-valued function classes, Technical Report, Department of Systems Engineering, Research School of Information Sciences and Engineering, Australian National University Canberra, Australia, 1996.
6. P.L. Bartlett, P.M. Long, More theorems about scale-sensitive dimensions and learning, in: Proc. 8th Annual Conf. Computational Learning Theory, Association for Computing Machinery, New York, 1995, pp. 392-401.
7. P.L. Bartlett, P.M. Long, R.C. Williamson, Fat-shattering and the learnability of real-valued functions, J. Comput. System Sci. 52 (1996) 434-452.
8. G.M. Benedek, A. Itai, Learnability by fixed distributions, in: Computational Learning Theory: Proc. 1988 Workshop, San Mateo, CA, Morgan Kaufman, pp. 80-90, 1988.
9. S.N. Bernstein, The Theory of Probabilities, Gastehizdat Publishing House, Moscow, 1946.
10. A. Blumer, A. Ehrenfeucht, D. Haussler, M.K. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, J. ACM 36 (1989) 929-965.
11. K.L. Buescher, P.R. Kumar, Learning by canonical smooth estimation, Part I: Simultaneous estimation, IEEE Trans. Automat. Control 41 (1996) 545-556.
12. K.L. Buescher, P.R. Kumar, Learning by canonical smooth estimation, Part II: learning and choice of model complexity, IEEE Trans. Automat. Control 41 (1996) 557-569.
13. L. Devroye, L. Györfi, G. Lugosi, A Probabilistic Theory of Pattern Recognition, Springer, New York, 1996.
14. L. Devroye, G. Lugosi, Lower bounds in pattern recognition and learning, Pattern Recognition 28 (1995) 1011-1018.
15. R.M. Dudley, S. Kulkarni, T. Richardson, O. Zeitouni, A metric entropy bound is not sufficient for learnability, IEEE Trans. Inform, Theory 40 (1994) 883-885.
16. D. Haussler, Decision theoretic generalizations of the PAC model for neural net and other learning applications, Inform. Comput. 100 (1992) 78-150.
17. M. Kearns, R.E. Shapire, Efficient distribution-free learning of probabilistic concepts, J. Comput. Sys. Sci. 48 (1994) 464-497.
18. S.R. Kulkarni, Problems of computational and information complexity in machine vision and learning, Ph.D. Thesis, Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, 1991.
19. W.S. Lee, P. Bartlett, R.C. Williamson, Efficient agnostic learning of neural networks with bounded fan-in, IEEE Trans. Inform. Theory 42 (1996) 2118-2132.
20. G. Lugosi, A. Nobel, Adaptive model selection using empirical complexities, 1996, submitted.
21. G. Lugosi, M. Pintér, A data-dependent skeleton estimate for learning, in Proc. 9th Annual ACM Conf. Computational Learning Theory, Association for Computing Machinery, New York, 1996, pp. 51-56.
22. A.B. Nobel, On uniform laws of averages, Ph.D. Thesis, Department of Statistics, Stanford University, Stanford, CA, 1992.
23. D. Pollard, Convergence of Stochastic Processes, Springer, New York, 1984.
24. D. Pollard, Rates of uniform almost sure convergence for empirical processes indexed by unbounded classes of functions, 1986, manuscript.
25. N. Sauer, On the density of families of sets, J. Combinatorial Theory Ser. A 13 (1972) 145-147.
26. J. Shawe-Taylor, P.L. Bartlett, R.C. Williamson, M. Anthony, A framework for structural risk minimization, in Proc 9th Annual Conf. Computational Learning Theory, Association of Computing Machinery, New York, 1996, p. 68-76.
27. V.N. Vapnik, Estimation of Dependencies Based on Empirical Data, Springer, New York, 1982.
28. V.N. Vapnik, A.Ya. Chervonenkis, On the uniform convergence of relative frequencies of events to their probabilities, Theory Probab. Appl. 16 (1971) 264-280.
29. V.N. Vapnik, A.Ya. Chervonenkis, Theory of Pattern Recognition, Nauka, Moscow, 1974 (in Russian); German translation: Theorie der Zeichenerkennung, Akademie Verlag, Berlin, 1979.
30. V.N. Vapnik, A.Ya. Chervonenkis, Theory of Pattern Recognition, Nauka, Moscow, 1974 (in Russian); German translation: Theorie der Zeichenerkennung, Akademie Verlag, Berlin, 1979.
31. V.N. Vapnik, A.Ya. Chervonenkis, Necessary and sufficient conditions for the uniform convergence of means to their expectations, Theory Probab. Appl. 26 (1981) 821-832.