English

AdaTask: Adaptive Multitask Online Learning

Machine Learning 2023-10-30 v2

Abstract

We introduce and analyze AdaTask, a multitask online learning algorithm that adapts to the unknown structure of the tasks. When the NN tasks are stochastically activated, we show that the regret of AdaTask is better, by a factor that can be as large as N\sqrt{N}, than the regret achieved by running NN 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.

Keywords

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 $1/(\alpha\eta_t)$

R2 v1 2026-06-24T11:34:32.204Z