Title
A Unifying Framework for Typical Multitask Multiple Kernel Learning Problems
Abbreviated Journal Title
Compos. Pt. B-Eng.
Keywords
Machine learning; optimization methods; pattern recognition; supervised; learning; support vector machines (SVMs); SUPPORT; SPARSITY; Computer Science, Artificial Intelligence; Computer Science, Hardware &; Architecture; Computer Science, Theory & Methods; Engineering, ; Electrical & Electronic
Abstract
Over the past few years, multiple kernel learning (MKL) has received significant attention among data-driven feature selection techniques in the context of kernel-based learning. MKL formulations have been devised and solved for a broad spectrum of machine learning problems, including multitask learning (MTL). Solving different MKL formulations usually involves designing algorithms that are tailored to the problem at hand, which is, typically, a nontrivial accomplishment. In this paper we present a general multitask multiple kernel learning (MT-MKL) framework that subsumes well-known MT-MKL formulations, as well as several important MKL approaches on single-task problems. We then derive a simple algorithm that can solve the unifying framework. To demonstrate the flexibility of the proposed framework, we formulate a new learning problem, namely partially-shared common space MT-MKL, and demonstrate its merits through experimentation.
Subjects
C. Li; M. Georgiopoulos;G. C. Anagnostopoulos
Volume
25
Issue/Number
7
Publication Date
1-1-2014
Document Type
Article
Language
English
First Page
1287
Last Page
1297
WOS Identifier
ISSN
2162-237X
Recommended Citation
"A Unifying Framework for Typical Multitask Multiple Kernel Learning Problems" (2014). Faculty Bibliography 2010s. 5681.
https://stars.library.ucf.edu/facultybib2010/5681
Comments
Authors: contact us about adding a copy of your work at STARS@ucf.edu