The shattering dimension of sets of linear functionals

We evaluate the shattering dimension of various classes of linear functionals on various symmetric convex sets. The proofs here relay mostly on methods from the local theory of normed spaces and include volume estimates, factorization techniques and tail estimates of norms, viewed as random variables on Euclidean spheres. The estimates of shattering dimensions can be applied to obtain error bounds for certain classes of functions, a fact which was the original motivation of this study. Although this can probably be done in a more traditional manner, we also use the approach presented here to determine whether several classes of linear functionals satisfy the uniform law of large numbers and the uniform central limit theorem.

[1]  Y. Gordon,et al.  Volume Formulas in Lp-Spaces , 1997 .

[2]  R. Dudley,et al.  Uniform and universal Glivenko-Cantelli classes , 1991 .

[3]  Peter L. Bartlett,et al.  Neural Network Learning - Theoretical Foundations , 1999 .

[4]  A generalization of Khintchine's inequality and its application in the theory of operator ideals , 1980 .

[5]  N. Tomczak-Jaegermann.  Banach-Mazur distances and finite-dimensional operator ideals , 1989 .

[6]  Shahar Mendelson,et al.  Rademacher averages and phase transitions in Glivenko-Cantelli classes , 2002, IEEE Trans. Inf. Theory.

[7]  E. Gluskin.  Norm estimates of certain p-absolutely summing operators , 1978 .

[8]  Y. Gordon,et al.  Volume ratios in $L_p$-spaces , 1999 .

[9]  Shahar Mendelson,et al.  Learnability in Hilbert Spaces with Reproducing Kernels , 2002, J. Complex..

[10]  A. W. van der Vaart,et al.  Uniform Central Limit Theorems , 2001 .

[11]  E. Berger.  UNIFORM CENTRAL LIMIT THEOREMS (Cambridge Studies in Advanced Mathematics 63) By R. M. D UDLEY : 436pp., £55.00, ISBN 0-521-46102-2 (Cambridge University Press, 1999). , 2001 .

[12]  V. Vapnik,et al.  Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations , 1982 .

[13]  Peter L. Bartlett,et al.  Localized Rademacher Complexities , 2002, COLT.

[14]  Bernhard Schölkopf,et al.  Generalization Performance of Regularization Networks and Support Vector Machines via Entropy Numbers of Compact Operators , 1998 .

[15]  Felipe Cucker,et al.  On the mathematical foundations of learning , 2001 .

[16]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[17]  K. Ball.  Volumes of sections of cubes and related problems , 1989 .

[18]  V. Milman,et al.  Asymptotic Theory Of Finite Dimensional Normed Spaces , 1986 .

[19]  A. Pajor,et al.  Sections of the unit ball of Ipn , 1988 .

[20]  M. Meyer,et al.  Sections of the Unit Ball of 1 , 2003 .

[21]  G. Pisier.  ASYMPTOTIC THEORY OF FINITE DIMENSIONAL NORMED SPACES (Lecture Notes in Mathematics 1200) , 1987 .

[22]  G. Pisier.  The volume of convex bodies and Banach space geometry , 1989 .

[23]  M. Talagrand.  Sharper Bounds for Gaussian and Empirical Processes , 1994 .

[24]  Noga Alon,et al.  Scale-sensitive dimensions, uniform convergence, and learnability , 1997, JACM.

[25]  Shahar Mendelson,et al.  A Few Notes on Statistical Learning Theory , 2002, Machine Learning Summer School.

[26]  O. Bousquet.  A Bennett concentration inequality and its application to suprema of empirical processes , 2002 .

[27]  Jon A. Wellner,et al.  Weak Convergence and Empirical Processes: With Applications to Statistics , 1996 .

[28]  S. Mendelson,et al.  Entropy and the combinatorial dimension , 2002, math/0203275.