Online Multi-task Learning with Hard Constraints
AbstractWe discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general class of tractable constraints, for which we introduce computationally efficient ways of selecting actions, essentially by reducing to an on-line shortest path problem. We briefly discuss ``tracking'' and ``bandit'' versions of the problem and extend the model in various ways, including non-additive global losses and uncountably infinite sets of tasks.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by HAL in its series Working Papers with number hal-00362643.
Date of creation: 13 Feb 2009
Date of revision:
Note: View the original document on HAL open archive server: http://hal.archives-ouvertes.fr/hal-00362643/en/
Contact details of provider:
Web page: http://hal.archives-ouvertes.fr/
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Friederike Mengel, 2007.
"Learning Across Games,"
Working Papers. Serie AD
2007-05, Instituto Valenciano de Investigaciones Económicas, S.A. (Ivie).
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (CCSD).
If references are entirely missing, you can add them using this form.