Fast learning rate of multiple kernel learning: Trade-off between sparsity and smoothness

03/02/2012
by   Taiji Suzuki, et al.
0

We investigate the learning rate of multiple kernel learning (MKL) with ℓ_1 and elastic-net regularizations. The elastic-net regularization is a composition 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 nonzero components of the ground truth is relatively small, and show sharper convergence rates than the learning rates have ever shown for both ℓ_1 and elastic-net regularizations. Our analysis reveals some relations between the choice of a regularization function and the performance. If the ground truth is smooth, we show a faster convergence rate for the elastic-net regularization with less conditions than ℓ_1-regularization; otherwise, a faster convergence rate for the ℓ_1-regularization is shown.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/02/2011

Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization

We investigate the learning rate of multiple kernel leaning (MKL) with e...
research
01/15/2010

Sparsity-accuracy trade-off in MKL

We empirically investigate the best trade-off between sparse and uniform...
research
03/27/2011

Sharp Convergence Rate and Support Consistency of Multiple Kernel Learning with Sparse and Dense Regularization

We theoretically investigate the convergence rate and support consistenc...
research
12/19/2013

Learning rates of l^q coefficient regularization learning with Gaussian kernel

Regularization is a well recognized powerful strategy to improve the per...
research
11/13/2010

Regularization Strategies and Empirical Bayesian Learning for MKL

Multiple kernel learning (MKL), structured sparsity, and multi-task lear...
research
03/14/2018

Multiplicative Updates for Elastic Net Regularized Convolutional NMF Under β-Divergence

We generalize the convolutional NMF by taking the β-divergence as the lo...
research
09/28/2009

SpicyMKL

We propose a new optimization algorithm for Multiple Kernel Learning (MK...

Please sign up or login with your details

Forgot password? Click here to reset