A note on different covering numbers in learning theory.

DOI10.1016/S0885-064X(03)00033-5zbMath1057.68044OpenAlexW2055979621MaRDI QIDQ1426052

Massimiliano Pontil

Publication date: 14 March 2004

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0885-064x(03)00033-5

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Related Items (13)

Estimates on compressed neural networks regression ⋮ Analysis of convergence performance of neural networks ranking algorithm ⋮ Concentration estimates for learning with unbounded sampling ⋮ Approximations of semicontinuous functions with applications to stochastic optimization and statistical estimation ⋮ Estimation of convergence rate for multi-regression learning algorithm ⋮ Unified approach to coefficient-based regularized regression ⋮ A discretized Tikhonov regularization method for a fractional backward heat conduction problem ⋮ Optimal rate of the regularized regression learning algorithm ⋮ The covering number for some Mercer kernel Hilbert spaces ⋮ Nonparametric nonlinear regression using polynomial and neural approximators: a numerical comparison ⋮ SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming ⋮ Estimates of learning rates of regularized regression via polyline functions ⋮ Unnamed Item

Cites Work

• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Regularization networks and support vector machines
• On the mathematical foundations of learning
• Scale-sensitive dimensions, uniform convergence, and learnability
• Probability Inequalities for Sums of Bounded Random Variables
• Theory of Reproducing Kernels
• Combinatorial methods in density estimation

This page was built for publication: A note on different covering numbers in learning theory.