Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies

DOI10.1214/18-EJS1399zbMath1410.62087arXiv1111.3781OpenAlexW2962925804WikidataQ129560965 ScholiaQ129560965MaRDI QIDQ1657947

Taiji Suzuki

Publication date: 14 August 2018

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1111.3781

zbMATH Keywords

regularizationreproducing kernel Hilbert spaceserror boundgeneralization errormultiple kernel learningfast learning rate

Mathematics Subject Classification ID

Hypothesis testing in multivariate analysis (62H15) Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• hgam
• SpicyMKL
• DeMat

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fast learning rate of multiple kernel learning: trade-off between sparsity and smoothness
• SpicyMKL: a fast algorithm for multiple kernel learning with thousands of kernels
• Sparsity in multiple kernel learning
• Differential evolution. A practical approach to global optimization. With CD-ROM.
• Multi-kernel regularized classifiers
• Advances in differential evolution
• High-dimensional additive modeling
• Information-theoretic determination of minimax rates of convergence
• A Bennett concentration inequality and its application to suprema of empirical processes
• Weak convergence and empirical processes. With applications to statistics
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Some results on Tchebycheffian spline functions and stochastic processes
• Local Rademacher complexities
• Error bounds for learning the kernel
• Support Vector Machines
• Learning Bounds for Support Vector Machines with Learned Kernels
• Minimax-optimal rates for sparse additive models over kernel classes via convex programming
• Model Selection and Estimation in Regression with Grouped Variables
• Convexity, Classification, and Risk Bounds
• New concentration inequalities in product spaces