A new concentration result for regularized risk minimizers

DOI10.1214/074921706000000897zbMath1127.68090arXivmath/0612779OpenAlexW1674949483MaRDI QIDQ3592321

Ingo Steinwart, Don Hush, Clint Scovel

Publication date: 12 September 2007

Published in: High Dimensional Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0612779

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Online gradient descent algorithms for functional data learning ⋮ Ivanov-Regularised Least-Squares Estimators over Large RKHSs and Their Interpolation Spaces ⋮ Partially linear functional quantile regression in a reproducing kernel Hilbert space ⋮ Nonparametric stochastic approximation with large step-sizes ⋮ A partially linear framework for massive heterogeneous data ⋮ Lower bounds for invariant statistical models with applications to principal component analysis ⋮ Unnamed Item ⋮ Multiscale regression on unknown manifolds ⋮ Radial kernels and their reproducing kernel Hilbert spaces ⋮ Optimal learning rates for least squares regularized regression with unbounded sampling ⋮ Statistical performance of support vector machines ⋮ Error analysis for coefficient-based regularized regression in additive models ⋮ Consistency of support vector machines using additive kernels for additive models ⋮ Estimation of convergence rate for multi-regression learning algorithm ⋮ Self-concordant analysis for logistic regression ⋮ Refined Generalization Bounds of Gradient Learning over Reproducing Kernel Hilbert Spaces ⋮ Learning rates for kernel-based expectile regression ⋮ The Goldenshluger-Lepski method for constrained least-squares estimators over RKHSs ⋮ Learning from dependent observations ⋮ Unnamed Item ⋮ Oracle inequalities for support vector machines that are based on random entropy numbers ⋮ Fast and strong convergence of online learning algorithms ⋮ Asymptotic normality of support vector machine variants and other regularized kernel methods ⋮ Learning under \((1 + \epsilon)\)-moment conditions ⋮ Unnamed Item ⋮ Unnamed Item