AdaTask: Adaptive Multitask Online Learning

TL;DR

AdaTask is a novel multitask online learning algorithm that adaptively learns task structures, achieving significantly improved regret bounds over independent task algorithms, with theoretical analysis and experimental validation.

Contribution

Introduces AdaTask, an adaptive algorithm for multitask online learning that leverages task structure to improve regret bounds, extending FTRL with a Mahalanobis norm.

Findings

AdaTask outperforms independent algorithms in regret.

The regret improvement can be as large as  times.

Experimental results confirm theoretical advantages.

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.