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 tasks are stochastically activated, we show that the regret of AdaTask is better, by a factor that can be as large as , than the regret achieved by running 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.
Cite
@article{arxiv.2205.15802,
title = {AdaTask: Adaptive Multitask Online Learning},
author = {Pierre Laforgue and Andrea Della Vecchia and Nicolò Cesa-Bianchi and Lorenzo Rosasco},
journal= {arXiv preprint arXiv:2205.15802},
year = {2023}
}
Comments
The proof of Theorem 3 is wrong: in the display equation below Equation (22), bottom of page 15, the gradient of $\phi_{t+1}$ is missing a factor $1/(\alpha\eta_t)$