Convex learning of multiple tasks and their structure
Reducing the amount of human supervision is a key problem in machine learning and a natural approach is that of exploiting the relations (structure) among different tasks. This is the idea at the core of multi-task learning. In this context a fundamental question is how to incorporate the tasks stru...
Main Authors: | Ciliberto, Carlo, Mroueh, Youssef, Poggio, Tomaso A, Rosasco, Lorenzo |
---|---|
Other Authors: | Center for Brains, Minds, and Machines |
Format: | Article |
Published: |
MIT Press
2017
|
Online Access: | http://hdl.handle.net/1721.1/112313 https://orcid.org/0000-0003-0249-5273 https://orcid.org/0000-0001-8798-1267 https://orcid.org/0000-0002-3944-0455 https://orcid.org/0000-0001-6376-4786 |
Similar Items
-
Regularization Predicts While Discovering Taxonomy
by: Mroueh, Youssef, et al.
Published: (2011) -
Multi-Class Learning: Simplex Coding And Relaxation Error
by: Mroueh, Youssef, et al.
Published: (2011) -
Multiclass learning with simplex coding
by: Mroueh, Youssef, et al.
Published: (2014) -
Learning with group invariant features: A Kernel perspective
by: Mroueh, Youssef, et al.
Published: (2017) -
Iterative regularization for learning with convex loss functions
by: Lin, Junhong, et al.
Published: (2018)