Efficient co-regularised least squares regression
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
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.
| Originalsprache | Englisch | 
|---|---|
| Titel | Proceedings of the 23rd international conference on Machine learning | 
| Herausgeber | William Cohen | 
| Anzahl der Seiten | 8 | 
| Verlag | Association for Computing Machinery, Inc | 
| Erscheinungsdatum | 01.01.2006 | 
| Seiten | 137-144 | 
| ISBN (Print) | 978-159593383-6, 1595933832 | 
| DOIs | |
| Publikationsstatus | Erschienen - 01.01.2006 | 
| Extern publiziert | Ja | 
| Veranstaltung | International Conference on Machine Learning - ICML 2006 - Carnegie Mellon University, Pittsburgh, USA / Vereinigte Staaten Dauer: 25.06.2006 → 29.06.2006 Konferenznummer: 23  | 
- Informatik
 - Wirtschaftsinformatik
 
