Optimal learning rates of \(l^p\)-type multiple kernel learning under general conditions

DOI10.1016/j.ins.2014.09.011zbMath1360.68691MaRDI QIDQ526680

Fanyin Zhou, Shao-Gao Lv

Publication date: 15 May 2017

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ins.2014.09.011

zbMATH Keywords

generalization ability; correlation measure; multiple kernel learning; local Rademacher complexity; kernel learning

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

An efficient kernel learning algorithm for semisupervised regression problems

Uses Software

• ElemStatLearn

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A fast algorithm for manifold learning by posing it as a symmetric diagonally dominant linear system
• Sparsity in multiple kernel learning
• Evolutionary combination of kernels for nonlinear feature transformation
• Sparsity in penalized empirical risk minimization
• Multi-kernel regularized classifiers
• Convex multi-task feature learning
• Optimal rates for the regularized least-squares algorithm
• Statistical performance of support vector machines
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• Learning rates of least-square regularized regression
• Local Rademacher complexities
• On the mathematical foundations of learning
• Support Vector Machines
• A Reproducing Kernel Hilbert Space Framework for Spike Train Signal Processing
• Advanced Lectures on Machine Learning
• Choosing multiple parameters for support vector machines