Efficient co-regularised least squares regression

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

In many applications, unlabelled examples are inexpensive and easy to obtain. Semi-supervised approaches try to utilise such examples to reduce the predictive error. In this paper, we investigate a semi-supervised least squares regression algorithm based on the co-learning approach. Similar to other semi-supervised algorithms, our base algorithm has cubic runtime complexity in the number of unlabelled examples. To be able to handle larger sets of unlabelled examples, we devise a semi-parametric variant that scales linearly in the number of unlabelled examples. Ex-periments show a significant error reduction by co-regularisation and a large runtime improvement for the semi-parametric approximation. Last but not least, we propose a distributed procedure that can be applied without collecting all data at a single site.

Original languageEnglish
Title of host publicationProceedings of the 23rd international conference on Machine learning
EditorsWilliam Cohen
Number of pages8
PublisherAssociation for Computing Machinery, Inc
Publication date01.01.2006
Pages137-144
ISBN (print)978-159593383-6, 1595933832
DOIs
Publication statusPublished - 01.01.2006
Externally publishedYes
EventICML '06 - Carnegie Mellon University, Pittsburgh, United States
Duration: 25.06.200629.06.2006
Conference number: 23

DOI