Sparsity-Agnostic Lasso Bandit

Min Hwan Oh*, Garud Iyengar, Assaf Zeevi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We consider a stochastic contextual bandit problem where the dimension d of the feature vectors is potentially large, however, only a sparse subset of features of cardinality s0 ≪ d affect the reward function. Essentially all existing algorithms for sparse bandits require a priori knowledge of the value of the sparsity index s0. This knowledge is almost never available in practice, and misspecification of this parameter can lead to severe deterioration in the performance of existing methods. The main contribution of this paper is to propose an algorithm that does not require prior knowledge of the sparsity index s0 and establish tight regret bounds on its performance under mild conditions. We also comprehensively evaluate our proposed algorithm numerically and show that it consistently outperforms existing methods, even when the correct sparsity index is revealed to them but is kept hidden from our algorithm.

Original languageEnglish
Title of host publicationProceedings of the 38th International Conference on Machine Learning, ICML 2021
PublisherML Research Press
Number of pages10
ISBN (Electronic)9781713845065
StatePublished - 2021
Externally publishedYes
Event38th International Conference on Machine Learning, ICML 2021 - Virtual, Online
Duration: 18 Jul 202124 Jul 2021

Publication series

NameProceedings of Machine Learning Research
ISSN (Electronic)2640-3498


Conference38th International Conference on Machine Learning, ICML 2021
CityVirtual, Online


Dive into the research topics of 'Sparsity-Agnostic Lasso Bandit'. Together they form a unique fingerprint.

Cite this