Abstract

: Let V ` f0; 1g n have Vapnik-Chervonenkis dimension d. Let M(k=n;V ) denote the cardinality of the largest W ` V such that any two distinct vectors in W differ on at least k indices. We show that M(k=n;V ) (cn=(k + d)) d for some constant c. This improves on the previous best result of ((cn=k) log(n=k)) d . This new result has applications in the theory of empirical processes. 1 The author gratefully acknowledges the support of the Mathematical Sciences Research Institute at UC Berkeley and ONR grant N00014-91-J-1162. 1 1 Statement of Results Let n be natural number greater than zero. Let V ` f0; 1g n . For a sequence of indices I = (i 1 ; . . . ; i k ), with 1 i j n, let V j I denote the projection of V onto I, i.e. V j I = f(v i 1 ; . . . ; v i k ) : (v 1 ; . . . ; v n ) 2 V g: If V j I = f0; 1g k then we say that V shatters the index sequence I. The Vapnik-Chervonenkis dimension of V is the size of the longest index sequence I that is shattered by V [VC71] (t...

Citations

816	On the uniform convergence of relative frequencies of events to their probabilities. Theory of Prob. and its - Vapnik, Chervonenkis - 1971
687	Estimation of dependences based on empirical data - Vapnik - 1982
565	Learnability and the Vapnik Chervonenkis dimension - Blumer, Ehrenfeucht, et al. - 1989
476	Concrete Mathematics - Graham, Knuth, et al. - 1989
457	Convergence of Stochastic Processes - Pollard - 1984
328	Decision theoretic generalization of the PAC model for neural net and other learning applications - Haussler - 1992
240	Epsilon-nets and simplex range queries - Haussler, Welzl - 1987
205	On the density of families of sets - Sauer - 1972
110	Central limit theorems for empirical measures - Dudley - 1979
98	Bounds on the Sample Complexity of Bayesian Learning Using Information Theory and the VC Dimension - Haussler, Kearns, et al. - 1991
96	A deterministic view of random sampling and its use in geometry, Combinatorica 10 - Chazelle, Friedman - 1990
77	Ratio limit theorems for empirical processes - Giné, Koltchinskii, et al. - 2003
68	A course on empirical processes - Dudley - 1984
50	Predicting f0,1g functions on randomly drawn points. Information and Computation 108(2): 212{261 - Haussler, Littlestone, et al. - 1994
38	Partition trees for triangle counting and other range searching problems - Welzl - 1988
34	Universal Donsker classes and metric entropy - Dudley - 1987
30	On the density of sets of vectors - Alon - 1983
30	A generalization of Sauer’s lemma - Haussler, Long - 1995
26	On the trace of finite sets - Frankl - 1983
26	The Glivenko–Cantelli problem - Talagrand - 1987
23	The shifting technique in extremal set theory - Frankl - 1987
16	Empirical Processes: Theory and Applications, Volume 2 - Pollard - 1990
15	Partitioning and geometric embedding of range spaces of finite VapnikChervonenkis dimension - Alon, Haussler, et al. - 1987
11	Densit'e et dimension. Annales de l'Institut Fourier - Assouad - 1983
9	The complexity of many faces in arrangements of lines and of segments - Edelsbrunner, Guibas, et al. - 1988
9	Existence of submatrices with all possible columns - Steele - 1978
9	Sharper bounds for empirical process - TALAGRAND - 1994
8	Induced subsets - Bondy - 1972
8	How to net a lot with little: Small epsilon-nets for disks and halfspaces - Matousek, Seidel, et al. - 1990
4	Quasi-optimal range searching and vc-dimensions - Chazelle, Welzl - 1989
4	Donsker classes of sets. Probability Theory and Related Fields, 78:169-191 - Talagrand - 1988
2	Donsker classes and random geometry - Talagrand - 1987