Open Problem: Model Selection for Contextual Bandits

Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo
Proceedings of Thirty Third Conference on Learning Theory, PMLR 125:3842-3846, 2020.

Abstract

In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees are possible for contextual bandit learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v125-foster20a, title = {Open Problem: Model Selection for Contextual Bandits}, author = {Foster, Dylan J. and Krishnamurthy, Akshay and Luo, Haipeng}, booktitle = {Proceedings of Thirty Third Conference on Learning Theory}, pages = {3842--3846}, year = {2020}, editor = {Abernethy, Jacob and Agarwal, Shivani}, volume = {125}, series = {Proceedings of Machine Learning Research}, month = {09--12 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v125/foster20a/foster20a.pdf}, url = {https://proceedings.mlr.press/v125/foster20a.html}, abstract = {In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees are possible for contextual bandit learning.} }
Endnote
%0 Conference Paper %T Open Problem: Model Selection for Contextual Bandits %A Dylan J. Foster %A Akshay Krishnamurthy %A Haipeng Luo %B Proceedings of Thirty Third Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2020 %E Jacob Abernethy %E Shivani Agarwal %F pmlr-v125-foster20a %I PMLR %P 3842--3846 %U https://proceedings.mlr.press/v125/foster20a.html %V 125 %X In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees are possible for contextual bandit learning.
APA
Foster, D.J., Krishnamurthy, A. & Luo, H.. (2020). Open Problem: Model Selection for Contextual Bandits. Proceedings of Thirty Third Conference on Learning Theory, in Proceedings of Machine Learning Research 125:3842-3846 Available from https://proceedings.mlr.press/v125/foster20a.html.

Related Material