The shattering dimension of sets of linear functionals.

DOI10.1214/009117904000000388MaRDI QIDQ1878980zbMATH OpenOpenAlexFDO

Authors Shahar Mendelson, Gideon Schechtman

Publication date 15 September 2004

Published in The Annals of Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/math/0410096

zbMATH Keywords

linear functionalsvolume estimatesfactorization techniquesshattering dimensiontail estimates of norms

Mathematics Subject Classification ID

Geometric probability and stochastic geometry (60D05) Central limit and other weak theorems (60F05) Strong limit theorems (60F15) Probabilistic methods in Banach space theory (46B09)

Abstract: 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.

Recommendations

• Vapnik-Chervonenkis type conditions and uniform Donsker classes of functions
• Entropy and the combinatorial dimension
• VC-dimensions of random function classes
• \(\ell\)-norm and its application to learning theory
• On the size of convex hulls of small sets

Cites work

• scientific article; zbMATH DE number 2089353 (Why is no real title available?)
• scientific article; zbMATH DE number 4103721 (Why is no real title available?)
• scientific article; zbMATH DE number 194093 (Why is no real title available?)
• scientific article; zbMATH DE number 194266 (Why is no real title available?)
• scientific article; zbMATH DE number 3608655 (Why is no real title available?)
• scientific article; zbMATH DE number 1950575 (Why is no real title available?)
• scientific article; zbMATH DE number 1422837 (Why is no real title available?)
• A Bennett concentration inequality and its application to suprema of empirical processes
• A generalization of Khintchine's inequality and its application in the theory of operator ideals
• Asymptotic theory of finite dimensional normed spaces. With an appendix by M. Gromov: Isoperimetric inequalities in Riemannian manifolds
• Entropy and the combinatorial dimension
• Gaussian characterization of uniform Donsker classes of functions
• Learnability in Hilbert spaces with reproducing kernels
• Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations
• Neural Network Learning
• Rademacher averages and phase transitions in Glivenko-Cantelli classes
• Scale-sensitive dimensions, uniform convergence, and learnability
• Sections of the unit ball of \(\ell ^ n_ p\)
• Sharper bounds for Gaussian and empirical processes
• Uniform Central Limit Theorems
• Uniform and universal Glivenko-Cantelli classes
• Volume formulas in \(L_p\)-spaces
• Weak convergence and empirical processes. With applications to statistics

Cited in

(3)

• scientific article; zbMATH DE number 1974502 (Why is no real title available?)
• Remarks on the geometry of coordinate projections in \(\mathbb{R}^n\)
• An improved uniform convergence bound with fat-shattering dimension

This page was built for publication: The shattering dimension of sets of linear functionals.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1878980)