AdaTask: Adaptive Multitask Online Learning
Not on the map. Why?
Abstract (arXiv)
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 √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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 38 references that are in the map. First posted on arXiv 31 May 2022.
Builds on
13 of 38 references.
References · 13
- 2017A Survey on Multi-Task Learningcited by 838
- 2019Introduction to Online Convex Optimizationcited by 793
- 2019Online Learning: A Modern Introduction Using Convex Optimizationcited by 407
- 2018Black-Box Reductions for Parameter-free Online Learning in Banach Spacescited by 124
- 2019Provable Guarantees for Gradient-Based Meta-Learningcited by 67
- 2019A Principled Approach for Learning Task Similarity in Multitask Learningcited by 32
- 2016Regret Bounds for Lifelong Learningcited by 19
- 2016Multi-Task Learning with Labeled and Unlabeled Taskscited by 17
- 2015Convex Learning of Multiple Tasks and their Structurecited by 13
- 2022Trace norm regularization for multi-task learning with scarce datacited by 10
- 2021Multitask Online Mirror Descentcited by 6
- 2017Nonparametric Online Regression while Learning the Metriccited by 2
1 more
Built on by
Citing papers per year: 2026: 1.
1 paper.