Error Bounds for lp-Norm Multiple Kernel Learning with Least Square Loss
The problem of learning the kernel function with linear combinations of multiple kernels has attracted considerable attention recently in machine learning. Specially, by imposing an lp-norm penalty on the kernel combination coefficient, multiple kernel learning (MKL) was proved useful and effective...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2012-01-01
|
| Series: | Abstract and Applied Analysis |
| Online Access: | http://dx.doi.org/10.1155/2012/915920 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The problem of learning the kernel function with linear combinations of multiple kernels has attracted considerable attention recently in machine learning. Specially, by imposing an lp-norm penalty on the kernel combination coefficient, multiple kernel learning (MKL) was proved useful and effective for theoretical analysis and practical applications (Kloft et al., 2009, 2011). In this paper, we present a theoretical analysis on the approximation error and learning ability of the lp-norm MKL. Our analysis shows explicit learning rates for lp-norm MKL and demonstrates some notable advantages compared with traditional kernel-based learning algorithms where the kernel is fixed. |
|---|---|
| ISSN: | 1085-3375 1687-0409 |