Convex Learning of Multiple Tasks and their Structure
This addresses the challenge of reducing human supervision in machine learning by exploiting task relations, though it appears incremental as it generalizes existing methods.
The paper tackles the problem of incorporating task structure into multi-task learning by proposing a convex optimization framework that encodes a-priori knowledge as a convex penalty, showing that tasks and their structure can be efficiently learned with convergence to the global minimum.
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.