Presentation 2011-03-29
Fast Convergence Rate of Multiple Kernel Learning with Elastic-Net Regularization
Taiji SUZUKI, Ryota TOMIOKA, Masashi SUGIYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We investigate the learning rate of multiple kernel leaning (MKL) with elastic-net regularization, which consists of an l_1-regularizer for inducing the sparsity and an l_2-regularizer for controlling the smoothness. We focus on a sparse setting where the total number of kernels is large but the number of non-zero components of the ground truth is relatively small, and prove that elastic-net MKL achieves the minimax learning rate on the l_2-mixed-norm ball. Our bound is sharper than the convergence rates ever shown, and has a property that the smoother the truth is, the faster the convergence rate is.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multiple Kernel Learning / Fast Convergence Rate / Sparse Learning / Elastic-net
Paper # IBISML2010-126
Date of Issue

Conference Information
Committee IBISML
Conference Date 2011/3/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information-Based Induction Sciences and Machine Learning (IBISML)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Fast Convergence Rate of Multiple Kernel Learning with Elastic-Net Regularization
Sub Title (in English)
Keyword(1) Multiple Kernel Learning
Keyword(2) Fast Convergence Rate
Keyword(3) Sparse Learning
Keyword(4) Elastic-net
1st Author's Name Taiji SUZUKI
1st Author's Affiliation Department of Mathematical Informatics, The University of Tokyo()
2nd Author's Name Ryota TOMIOKA
2nd Author's Affiliation Department of Mathematical Informatics, The University of Tokyo
3rd Author's Name Masashi SUGIYAMA
3rd Author's Affiliation Department of Computer Science, Tokyo Institute of Technology
Date 2011-03-29
Paper # IBISML2010-126
Volume (vol) vol.110
Number (no) 476
Page pp.pp.-
#Pages 8
Date of Issue