IC Mondays seminars - Multi-task Learning: Theory and Practice
Event details
| Date | 19.04.2010 |
| Hour | 16:15 |
| Speaker | Dr. Massimiliano Pontil, University College London, Computer Science Department |
| Location |
INM 202
|
| Category | Conferences - Seminars |
Astract
We discuss the problem of estimating a structured matrix with a large number of elements. A key motivation for this problem occurs in multi-task learning. In this case, the columns of the matrix correspond to the parameters of different regression or classification tasks, and there is structure due to relations between the tasks. We present a general method to learn the tasks' parameters as well as their structure. Our approach is based on solving a convex optimization problem, involving a data term and a penalty term. We highlight different types of penalty terms which are of practical and theoretical importance. They implement structural relations between the tasks and achieve a sparse representations of parameters. We address computational issues as well as the predictive performance of the method. Finally we discuss how these ideas can be extended to learn non-linear task functions by means of reproducing kernels.
Biography
Massimiliano Pontil is a Reader and EPSRC Advanced Research Fellow in the Department of Computer Science at University College London. His research interests are in the area of machine learning with a focus on regularization methods, convex optimization and statistical estimation. He received the equivalent of an MSc and a PhD in Physics from the University of Genova in 1994 and 1999, respectively. He has also held visiting positions at several universities and was a Postdoctoral Fellow at the Massachusetts Institute of Technology.
Links
Practical information
- General public
- Free
Contact
- G.Rochat