A note on a scale-sensitive dimension of linear bounded functionals in Banach Spaces
We show that “B is of type p > 1” is a necessary and sufficient condition for a learnability of a class of linear bounded functionals with norm ≤ 1 restrited to the unit ball in Banach Space B. On the way we give very short probabilistic proof for Vapnik's result (Hilbert Space and improved) and improve our result with Pascal Koiran for convex halls of indicator functions. The approach we use in this paper allows to connect various results about learnability and approximation.
KeywordsVC-dimension scale-sensitive dimension Banach Spaces
Unable to display preview. Download preview PDF.
- [ABCH]N. Alon, S. Ben-David, N. Cesa-Bianchi, and D. Haussler, “Scale-sensitive dimensions, uniform convergence, and learnability,” in Proc. 34th IEEE Symp. on FOCS, pages 292–301, 1993.Google Scholar
- [KS94]M. Kearns and R. Schapire, “Efficient distribution-free learning of probabilistic concepts,” Journal of Comp. and System Sciences, 48(3): 464–497, 1994.Google Scholar
- [GK95]L. Gurvits and P. Koiran, “Approximation and learning of convex superpositions,” in Proc. of Computational Learning Theory: EuroCOLT-95, Springer, pages 222–236, 1995.Google Scholar
- [Va95]Vladimir N. Vapnik, “The nature of statistical learning theory,” Springer, 1995.Google Scholar
- [DDGS93]C. Darken, M. Donahue, L. Gurvits and E. Sontag, “Rate of approximation results motivated by robust neural network learning,” in Proc. of the Sixth Annual ACM COLT. pages 303–309, 1993.Google Scholar
- [DGDS97]M. Donahue, L. Gurvits, C. Darken and E. Sontag, “Ratex of convex approximations in Non-Hibert spaces,” Constractive Approximation, (1997) 13: 187–220.Google Scholar
- [Ba91]A.R. Barron, “Approximation and estimation bounds for artificial neural networks,” in “Proc. Fourth Annual Workshop on Computational Learning Theory,” Morgan Kaufmann, pages 243–249, 1991.Google Scholar
- [Jo92]L.K. Jones, “A simple lemma on greedy approximations in Hilbert space and convergence rates for projection pursuit regression and neural network training,” Annals of Statistics, 20:608–613, 1992.Google Scholar
- [BH]E.B. Baum and D. Haussler, “What size net gives valid generalization?” Neural Computation, 1:151–160, 1989.Google Scholar
- [LT91]M. Ledoux and M. Talagrand, “Probability in Banach Space,” Springer-Verlag, 1991.Google Scholar
- [LT92]J. Lindenstrauss and L. Tzafriri, “Classical Banach Spaces (second and third books)”, Springer-Verlag, 1979.Google Scholar