This paper collects together a miscellany of results originally motivated by the analysis of the generalization performance of the “maximum-margin ” algorithm due to Vapnik and others. The key feature of the paper is its operator-theoretic viewpoint. New bounds on covering numbers for classes related to Maximum Margin classes are derived directly without making use of a combinatorial dimension such as the VC-dimension. Specific contents of the paper include: ¯ a new and self-contained proof of Maurey’s theorem and some generalizations with small explicit values of constants; ¯ bounds on the covering numbers of maximum margin classes suitable for the analysis of their generalization performance; ¯ the extension of such classes to those induc...
Abstract—In this paper, we study the covering numbers of the space of convex and uniformly bounded f...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...
We solve Talagrand's entropy problem: The L2-covering numbers of every uniformly bounded class of fu...
We derive new bounds on covering numbers for hypothesis classes generated by convex combinations of ...
We derive new bounds for the generalization error of feature space machines, such as support vector ...
In the study of hilbertian subspaces of Banach spaces and lower estimates of norms by hilbertian nor...
Let (S,A,P) be a probability space and let Pn be the empirical measure based on i.i.d. sample (X1,.....
This chapter contains sections titled: Introduction, Tools from Functional Analysis, Convex Combinat...
We investigate measures of complexity of function classes based on continuity moduli of Gaussian and...
The paper presents diverse methods for estimating the covering number of a precompact subset of a Ba...
We find a sharp combinatorial bound for the metric entropy of sets in R^n and general class...
AbstractWe consider the class M of monotonically increasing binary output functions. M has considera...
AbstractWe complement classical results on the interpolation of entropy numbers as well as certain s...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...
Abstract—In this paper, we study the covering numbers of the space of convex and uniformly bounded f...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...
We solve Talagrand's entropy problem: The L2-covering numbers of every uniformly bounded class of fu...
We derive new bounds on covering numbers for hypothesis classes generated by convex combinations of ...
We derive new bounds for the generalization error of feature space machines, such as support vector ...
In the study of hilbertian subspaces of Banach spaces and lower estimates of norms by hilbertian nor...
Let (S,A,P) be a probability space and let Pn be the empirical measure based on i.i.d. sample (X1,.....
This chapter contains sections titled: Introduction, Tools from Functional Analysis, Convex Combinat...
We investigate measures of complexity of function classes based on continuity moduli of Gaussian and...
The paper presents diverse methods for estimating the covering number of a precompact subset of a Ba...
We find a sharp combinatorial bound for the metric entropy of sets in R^n and general class...
AbstractWe consider the class M of monotonically increasing binary output functions. M has considera...
AbstractWe complement classical results on the interpolation of entropy numbers as well as certain s...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...
Abstract—In this paper, we study the covering numbers of the space of convex and uniformly bounded f...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...
We derive new bounds for the generalization error of kernel machines, such as support vector machine...