SVM+ regression and Multi-Task Learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Scopus citations


Exploiting additional information to improve traditional inductive learning is an active research area in machine learning. In many supervised-Iearning applications, training data can be naturally separated into several groups, and incorporating this group information into learning may improve generalization. Recently, Vapnik [9] proposed general approach to formalizing such problems, known as Learning With Structured Data (LWSD) and its SVM-based optimization formulation called SVM+. Liang and Cherkassky [5,6] showed empirical validation of SVM+ for classification, and its connections to Multi-Task Learning (MTL) approaches in machine learning. This paper builds upon this recent work [5,6,9] and describes a new methodology for regression problems, combining Vapnik's SVM+ regression [9] and the MTL classification setting [6], for regression problems. We also show empirical comparisons between standard SVM regression, SVM+, and proposed SVM+MTL regression method. Practical implementation of new learning technologies, such as SVM+, is often hindered by their complexity, i.e. large number of tuning parameters (vs standard inductive SVM regression). To this end, we provide a practical scheme for model selection that combines analytic selection of parameters for SVM regression [3] and resampling-based methods for selecting model parameters specific to SVM+ and SVM+MTL.

Original languageEnglish (US)
Title of host publication2009 International Joint Conference on Neural Networks, IJCNN 2009
Number of pages7
StatePublished - Nov 18 2009
Event2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States
Duration: Jun 14 2009Jun 19 2009

Publication series

NameProceedings of the International Joint Conference on Neural Networks


Other2009 International Joint Conference on Neural Networks, IJCNN 2009
CountryUnited States
CityAtlanta, GA

Fingerprint Dive into the research topics of 'SVM+ regression and Multi-Task Learning'. Together they form a unique fingerprint.

Cite this