AdaTask: Adaptive Multitask Online Learning

Abstract

We introduce and analyze AdaTask, a multitask online learning algorithm that adapts to the unknown structure of the tasks. When the $N$ tasks are stochastically activated, we show that the regret of AdaTask is better, by a factor that can be as large as $\sqrt{N}$, than the regret achieved by running $N$ independent algorithms, one for each task. AdaTask can be seen as a comparator-adaptive version of Follow-the-Regularized-Leader with a Mahalanobis norm potential. Through a variational formulation of this potential, our analysis reveals how AdaTask jointly learns the tasks and their structure. Experiments supporting our findings are presented.

The proof of Theorem 3 is wrong: in the display equation below Equation (22), bottom of page 15, the gradient of ${\varphi }_{t+1}$ is missing a factor $1/(\alpha {\eta }_t)$