We present sharp bounds on the localized Rademacher averages of the unit ball in a reproducing kernel Hilbert space in terms of the eigenvalues of the integral operator associated with the kernel. We use this result to estimate the performance of the empirical minimization algorithm when the base class is the unit ball of the reproducing kernel Hilbert space
AbstractMetric entropy quantities, like covering numbers or entropy numbers, and positive definite k...
The paper studies convex stochastic optimization problems in a reproducing kernel Hilbert space (RKH...
In this paper we develop a novel probabilistic generalization bound for regular-ized kernel learning...
Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning...
Abstract: New non-asymptotic uniform error bounds for approximating func-tions in reproducing kernel...
We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of com...
AbstractBy the aid of the properties of the square root of positive operators we refine the consiste...
Learning mappings between infinite-dimensional function spaces has achieved empirical success in man...
We find probability error bounds for approximations of functions f in a separable reproducing kernel...
Learning from data under constraints on model complexity is studied in terms of rates of approximate...
Learning from data under constraints on model complexity is studied in terms of rates of approximate...
AbstractWe explore the question of the learnability of classes of functions contained in a Hilbert s...
AbstractIn this paper, we investigate the generalization performance of a regularized ranking algori...
AbstractThe covering number of a ball of a reproducing kernel Hilbert space as a subset of the conti...
Copyright © 2010 The MIT PressCopyright © 2010 Massachusetts Institute of TechnologyWe develop a nov...
AbstractMetric entropy quantities, like covering numbers or entropy numbers, and positive definite k...
The paper studies convex stochastic optimization problems in a reproducing kernel Hilbert space (RKH...
In this paper we develop a novel probabilistic generalization bound for regular-ized kernel learning...
Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning...
Abstract: New non-asymptotic uniform error bounds for approximating func-tions in reproducing kernel...
We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of com...
AbstractBy the aid of the properties of the square root of positive operators we refine the consiste...
Learning mappings between infinite-dimensional function spaces has achieved empirical success in man...
We find probability error bounds for approximations of functions f in a separable reproducing kernel...
Learning from data under constraints on model complexity is studied in terms of rates of approximate...
Learning from data under constraints on model complexity is studied in terms of rates of approximate...
AbstractWe explore the question of the learnability of classes of functions contained in a Hilbert s...
AbstractIn this paper, we investigate the generalization performance of a regularized ranking algori...
AbstractThe covering number of a ball of a reproducing kernel Hilbert space as a subset of the conti...
Copyright © 2010 The MIT PressCopyright © 2010 Massachusetts Institute of TechnologyWe develop a nov...
AbstractMetric entropy quantities, like covering numbers or entropy numbers, and positive definite k...
The paper studies convex stochastic optimization problems in a reproducing kernel Hilbert space (RKH...
In this paper we develop a novel probabilistic generalization bound for regular-ized kernel learning...
DOI
Add to ORKG