论文信息 - Embedding with a Lipschitz function

Embedding with a Lipschitz function

We investigate a new notion of embedding of subsets of {−1, 1}n in a given normed space, in a way which preserves the structure of the given set as a class of functions on {1, ..., n}. This notion is an extension of the margin parameter often used in Nonparametric Statistics. Our main result is that even when considering “small” subsets of {−1, 1}n, the vast majority of such sets do not embed in a better way than the entire cube in any normed space that satisfies a minor structural assumption.

Shahar Mendelson | S. Mendelson

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

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

[3] A. Giannopoulos. A NOTE ON THE BANACH-MAZUR DISTANCE TO THE CUBE , 1995 .

[4] Shai Ben-David,et al. Limitations of Learning Via Embeddings in Euclidean Half Spaces , 2003, J. Mach. Learn. Res..

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

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

[7] V. Koltchinskii,et al. Empirical margin distributions and bounding the generalization error of combined classifiers , 2002, math/0405343.

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

[9] Ralf Herbrich,et al. Learning Kernel Classifiers , 2001 .

[10] Yoav Freund,et al. Large Margin Classification Using the Perceptron Algorithm , 1998, COLT.

[11] Peter L. Bartlett,et al. Improved Generalization Through Explicit Optimization of Margins , 2000, Machine Learning.

[12] Gideon Schechtman,et al. The shattering dimension of sets of linear functionals , 2004 .

[13] Alexander J. Smola,et al. Learning with kernels , 1998 .

[14] B. Bollobás,et al. Extremal Graph Theory , 2013 .

[15] Vladimir Vapnik,et al. Statistical learning theory , 1998 .