Maurer, A;
Pontil, M;
Romera-Paredes, B;
(2016)
The benefit of multitask representation learning.
Journal of Machine Learning Research
, 17
(81)
pp. 1-32.
Preview |
Text
Pontil_the benefit of multitask_vor.pdf - Published Version Download (405kB) | Preview |
Abstract
We discuss a general method to learn data representations from multiple tasks. We provide a justification for this method in both settings of multitask learning and learning-to-learn. The method is illustrated in detail in the special case of linear feature learning. Conditions on the theoretical advantage offered by multitask representation learning over independent task learning are established. In particular, focusing on the important example of half-space learning, we derive the regime in which multitask representation learning is beneficial over independent task learning, as a function of the sample size, the number of tasks and the intrinsic data dimensionality. Other potential applications of our results include multitask feature learning in reproducing kernel Hilbert spaces and multilayer, deep networks.
| Type: | Article |
|---|---|
| Title: | The benefit of multitask representation learning |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | http://jmlr.org/papers/v17/ |
| Language: | English |
| Additional information: | Copyright © 2017 The Author(s). All rights reserved. |
| Keywords: | Learning-to-learn, multitask learning, representation learning, statistical learning theory, transfer learning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/1503650 |
Archive Staff Only
 |
View Item |
