On the convergence rate of l_p-norm multiple kernel learning

zbMATH Open1433.68356arXiv1103.0790MaRDI QIDQ5405196FDOQ5405196

Authors: Marius Kloft, Gilles Blanchard 

Publication date: 1 April 2014

Full work available at URL: https://arxiv.org/abs/1103.0790

Recommendations

• Error bounds for \(l^p\)-norm multiple kernel learning with least square loss
• Optimal learning rates of \(l^p\)-type multiple kernel learning under general conditions
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Sparsity in multiple kernel learning
• scientific article; zbMATH DE number 6253899

zbMATH Keywords

multiple kernel learninggeneralization boundslocal Rademacher complexitylearning kernels

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)

Cited In (14)

• Title not available (Why is that?)
• Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies
• Title not available (Why is that?)
• An efficient kernel learning algorithm for semisupervised regression problems
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Online primal-dual learning for a data-dependent multi-kernel combination model with multiclass visual categorization applications
• Error bounds for \(l^p\)-norm multiple kernel learning with least square loss
• Multi-task and lifelong learning of kernels
• Training Lp norm multiple kernel learning in the primal
• Fast generalization error bound of deep learning without scale invariance of activation functions
• Refined Rademacher chaos complexity bounds with applications to the multikernel learning problem
• Fast learning rate of multiple kernel learning: trade-off between sparsity and smoothness
• Optimal learning rates of \(l^p\)-type multiple kernel learning under general conditions
• Analysis of target data-dependent greedy kernel algorithms: convergence rates for \(f\)-, \(f \cdot P\)- and \(f/P\)-greedy

This page was built for publication: On the convergence rate of \(l_{p}\)-norm multiple kernel learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405196)