Multi-task and meta-learning with sparse linear bandits

Leonardo Cella; Massimiliano Pontil

UAI 2021poster22 citations

Multi-task and meta-learning with sparse linear bandits

Abstract

Motivated by recent developments on meta-learning with linear contextual bandit tasks, we study the benefit of feature learning in both the multi-task and meta-learning settings. We focus on the case that the task weight vectors are

BibTeX

@InProceedings{pmlr-v161-cella21a,
  title = 	 {Multi-task and meta-learning with sparse linear bandits},
  author =       {Cella, Leonardo and Pontil, Massimiliano},
  booktitle = 	 {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence},
  pages = 	 {1692--1702},
  year = 	 {2021},
  editor = 	 {de Campos, Cassio and Maathuis, Marloes H.},
  volume = 	 {161},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {27--30 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v161/cella21a/cella21a.pdf},
  url = 	 {https://proceedings.mlr.press/v161/cella21a.html},
  abstract = 	 {Motivated by recent developments on meta-learning with linear contextual bandit tasks, we study the benefit of feature learning in both the multi-task and meta-learning settings. We focus on the case that the task weight vectors are