Fully online classification by regularization

DOI10.1016/J.ACHA.2006.12.001zbMath1124.68099OpenAlexW1977073705MaRDI QIDQ2381648

Ding-Xuan Zhou, Gui-Bo Ye

Publication date: 18 September 2007

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.acha.2006.12.001

zbMATH Keywords

regularizationerror analysisreproducing kernel Hilbert spacesonline learningclassification algorithm

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (18)

LEAST SQUARE REGRESSION WITH COEFFICIENT REGULARIZATION BY GRADIENT DESCENT ⋮ Generalization properties of doubly stochastic learning algorithms ⋮ Distributed regression learning with coefficient regularization ⋮ Convergence of online pairwise regression learning with quadratic loss ⋮ Convergence analysis of online learning algorithm with two-stage step size ⋮ Online learning for quantile regression and support vector regression ⋮ Unregularized online learning algorithms with general loss functions ⋮ Learning and approximation by Gaussians on Riemannian manifolds ⋮ Learning gradients by a gradient descent algorithm ⋮ Logistic classification with varying gaussians ⋮ Unnamed Item ⋮ Unregularized online algorithms with varying Gaussians ⋮ ONLINE LEARNING WITH MARKOV SAMPLING ⋮ Learning rates of gradient descent algorithm for classification ⋮ Moving quantile regression ⋮ SVM LEARNING AND L^p APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS ⋮ ONLINE REGRESSION WITH VARYING GAUSSIANS AND NON-IDENTICAL DISTRIBUTIONS ⋮ Online Classification with Varying Gaussians

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Model selection for regularized least-squares algorithm in learning theory
• Multi-kernel regularized classifiers
• Relative expected instantaneous loss bounds
• Support vector machines are universally consistent
• On the Bayes-risk consistency of regularized boosting methods.
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Regularization networks and support vector machines
• Online learning algorithms
• Shannon sampling. II: Connections to learning theory
• Learning theory estimates via integral operators and their approximations
• On the Generalization Ability of On-Line Learning Algorithms
• Online Regularized Classification Algorithms
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Shannon sampling and function reconstruction from point values
• Online Learning with Kernels
• Learning Theory
• STABILITY RESULTS IN LEARNING THEORY
• Convexity, Classification, and Risk Bounds
• Theory of Reproducing Kernels

This page was built for publication: Fully online classification by regularization