Back to Search
Start Over
Convex formulation for multi-task L1-, L2-, and LS-SVMs
- Source :
- Biblos-e Archivo. Repositorio Institucional de la UAM, instname
- Publication Year :
- 2021
- Publisher :
- Elsevier BV, 2021.
-
Abstract
- Quite often a machine learning problem lends itself to be split in several well-defined subproblems, or tasks. The goal of Multi-Task Learning (MTL) is to leverage the joint learning of the problem from two different perspectives: on the one hand, a single, overall model, and on the other hand task-specific models. In this way, the found solution by MTL may be better than those of either the common or the task-specific models. Starting with the work of Evgeniou et al., support vector machines (SVMs) have lent themselves naturally to this approach. This paper proposes a convex formulation of MTL for the L1-, L2- and LS-SVM models that results in dual problems quite similar to the single-task ones, but with multi-task kernels; in turn, this makes possible to train the convex MTL models using standard solvers. As an alternative approach, the direct optimal combination of the already trained common and task-specific models can also be considered. In this paper, a procedure to compute the optimal combining parameter with respect to four different error functions is derived. As shown experimentally, the proposed convex MTL approach performs generally better than the alternative optimal convex combination, and both of them are better than the straight use of either common or task-specific models<br />With partial support from Spain’s grant TIN2016-76406-P. Work supported also by the UAM–ADIC Chair for Data Science and Machine Learning.
- Subjects :
- Informática
LS-SVM
L1-SVM
Computer science
Convex model combination
Cognitive Neuroscience
Regular polygon
Computer Science Applications
Dual (category theory)
Support vector machine
L2-SVM
Task (computing)
Multi-task learning
Artificial Intelligence
Optimal combination
Leverage (statistics)
Convex combination
Algorithm
Subjects
Details
- ISSN :
- 09252312
- Volume :
- 456
- Database :
- OpenAIRE
- Journal :
- Neurocomputing
- Accession number :
- edsair.doi.dedup.....65a0c85f70721ef5cb00294511fce575