Approximation and Learning of Convex Superpositions

Journal of Computer and System Sciences

Volumn 55, Issue 1, 1997, Pages 161-170

  Gurvits, Leonid ^a   Koiran, Pascal ^b  

^a NEC LABORATORIES AMERICA   (United States)

^b UNIV LYON   (France)

Author keywords

[No Author keywords available]

Indexed keywords

FUNCTIONS; LEARNING SYSTEMS; MATHEMATICAL TECHNIQUES; NEURAL NETWORKS;

CONVEX SUPERPOSITIONS;

COMPUTER SCIENCE;

EID: 0031212925     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1006/jcss.1997.1506     Document Type: Article

References (21)

1. N. Alon, S. Ben-David, N. Cesa-Bianchi, and D. Haussler, Scale-sensitive dimensions, uniform convergence, and learnability, in "Proc. 34th IEEE Symposium on Foundations of Computer Science, 1993," pp. 292-301.
2. A. Barron, Neural net approximation, in "Proc. 7th Yale Workshop on Adaptative and Learning Systems, 1992."
3. A. Barron, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Trans. Inform. Theory 39, No. 3 (May 1993), 930-945.
4. P. Bartlett, P. Long, and R. Williamson, Fat-shattering and the learnability of real-valued functions, in "Proc. 7th Annual ACM Conference on Computational Learning Theory, 1994," pp. 299-310.
5. E. B. Baum and D. Haussler, What size net gives valide generalization?, Neural Comput. 1 (1989), 151-160.
6. A. Blumer, A. Ehrenfeucht, D. Haussler, and M. Warmuth, Learn-ability and the Vapnik-Chervonenkis dimension, Assoc. Comput. Machin. 36, No. 4 (1989), 929-965.
7. M. Donahue, L. Gurvits, C. Darken, and E. Sontag, "Rates of Convex Approximations in Non-Hilbert Spaces," Tech. Rep. 1251, Institute for Mathematics and Its Applications, University of Minnesota, Minneapolis, MN 55455, Sep. 1994.
8. R. M. Dudley, Central limit theorems for empirical measures, Ann. Probab. 6, No. 6 (1978), 899-929.
9. R. M. Dudley, Universal Donsker classes and metric entropy, Ann. Probab. 15, No. 4 (1987), 1306-1326.
10. R. M. Dudley, "Real Analysis and probability," Brooks/Cole, Pacific Grove, CA, 1989.
11. P. Halmos, "Lectures on Ergodic Theory," Chelsea, New York, 1956.
12. D. Haussler, Decision theoretic generalizations of the PAC model for neural nets and other learning applications, Inform. and Comput. 100 (1992), 78-150.
13. M. Kearns and R. Schapire, Efficient distribution-free learning of probabilistic concepts, J. Comput. System Sci. 48, No. 3 (1994), 464-497.
14. M. Laskowski, Vapnik-Chervonenkis classes of definable sets, J. London Math. Soc. 45, No. 2 (1992), 377-384.
15. M. Ledoux and M. Talagrand, "Probability in Banach Spaces," Springer-Verlag, New York/Berlin, 1991.
16. J. Matousek, E. Welzl, and L. Wernisch, Discrepancy and approximation for bounded VC-dimension, Combinatorica 13, No. 4 (1993), 455-466.
17. D. Nolan and D. Pollard, U-processes: Rates of convergences, Ann. Statist. 15, No. 2 (1987), 780-799.
18. R. Phelps, "Lectures on Choquet's Theorem," Van Nostrand Mathematical Studies, Van Nostrand, New York, 1966.
19. D. Pollard, "Convergence of Stochastic Processes," Springer-Verlag, New York/Berlin, 1984.
20. V. Vapnik, "Estimation of Dependences Based on Empirical Data," Springer Series in Statistics, Springer-Verlag, New York/Berlin, 1982.
21. L. Gurvits, "A Note on a Scale-Sensitive Dimension of Linear Bounded Functionals in Banach Spaces," NEC Res. Inst. Technical Report, 1997.