Convex Learning of Multiple Tasks and their Structure

Carlo Ciliberto, Youssef Mroueh, Tomaso Poggio, Lorenzo Rosasco
Proceedings of the 32nd International Conference on Machine Learning, PMLR 37:1548-1557, 2015.

Abstract

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 structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches. Within this framework, we show that tasks and their structure can be efficiently learned considering a convex optimization problem that can be approached by means of block coordinate methods such as alternating minimization and for which we prove convergence to the global minimum.

Cite this Paper

BibTeX
@InProceedings{pmlr-v37-ciliberto15, title = {Convex Learning of Multiple Tasks and their Structure}, author = {Ciliberto, Carlo and Mroueh, Youssef and Poggio, Tomaso and Rosasco, Lorenzo}, booktitle = {Proceedings of the 32nd International Conference on Machine Learning}, pages = {1548--1557}, year = {2015}, editor = {Bach, Francis and Blei, David}, volume = {37}, series = {Proceedings of Machine Learning Research}, address = {Lille, France}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v37/ciliberto15.pdf}, url = {https://proceedings.mlr.press/v37/ciliberto15.html}, abstract = {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 structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches. Within this framework, we show that tasks and their structure can be efficiently learned considering a convex optimization problem that can be approached by means of block coordinate methods such as alternating minimization and for which we prove convergence to the global minimum.} }
Endnote
%0 Conference Paper %T Convex Learning of Multiple Tasks and their Structure %A Carlo Ciliberto %A Youssef Mroueh %A Tomaso Poggio %A Lorenzo Rosasco %B Proceedings of the 32nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2015 %E Francis Bach %E David Blei %F pmlr-v37-ciliberto15 %I PMLR %P 1548--1557 %U https://proceedings.mlr.press/v37/ciliberto15.html %V 37 %X 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 structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches. Within this framework, we show that tasks and their structure can be efficiently learned considering a convex optimization problem that can be approached by means of block coordinate methods such as alternating minimization and for which we prove convergence to the global minimum.
RIS
TY - CPAPER TI - Convex Learning of Multiple Tasks and their Structure AU - Carlo Ciliberto AU - Youssef Mroueh AU - Tomaso Poggio AU - Lorenzo Rosasco BT - Proceedings of the 32nd International Conference on Machine Learning DA - 2015/06/01 ED - Francis Bach ED - David Blei ID - pmlr-v37-ciliberto15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 37 SP - 1548 EP - 1557 L1 - http://proceedings.mlr.press/v37/ciliberto15.pdf UR - https://proceedings.mlr.press/v37/ciliberto15.html AB - 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 structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches. Within this framework, we show that tasks and their structure can be efficiently learned considering a convex optimization problem that can be approached by means of block coordinate methods such as alternating minimization and for which we prove convergence to the global minimum. ER -
APA
Ciliberto, C., Mroueh, Y., Poggio, T. & Rosasco, L.. (2015). Convex Learning of Multiple Tasks and their Structure. Proceedings of the 32nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 37:1548-1557 Available from https://proceedings.mlr.press/v37/ciliberto15.html.

Related Material