Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits

Chuanhao Li, Hongning Wang
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:6529-6553, 2022.

Abstract

Linear contextual bandit is a popular online learning problem. It has been mostly studied in centralized learning settings. With the surging demand of large-scale decentralized model learning, e.g., federated learning, how to retain regret minimization while reducing communication cost becomes an open challenge. In this paper, we study linear contextual bandit in a federated learning setting. We propose a general framework with asynchronous model update and communication for a collection of homogeneous clients and heterogeneous clients, respectively. Rigorous theoretical analysis is provided about the regret and communication cost under this distributed learning framework; and extensive empirical evaluations demonstrate the effectiveness of our solution.

Cite this Paper

BibTeX
@InProceedings{pmlr-v151-li22e, title = { Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits }, author = {Li, Chuanhao and Wang, Hongning}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {6529--6553}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/li22e/li22e.pdf}, url = {https://proceedings.mlr.press/v151/li22e.html}, abstract = { Linear contextual bandit is a popular online learning problem. It has been mostly studied in centralized learning settings. With the surging demand of large-scale decentralized model learning, e.g., federated learning, how to retain regret minimization while reducing communication cost becomes an open challenge. In this paper, we study linear contextual bandit in a federated learning setting. We propose a general framework with asynchronous model update and communication for a collection of homogeneous clients and heterogeneous clients, respectively. Rigorous theoretical analysis is provided about the regret and communication cost under this distributed learning framework; and extensive empirical evaluations demonstrate the effectiveness of our solution. } }
Endnote
%0 Conference Paper %T Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits %A Chuanhao Li %A Hongning Wang %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-li22e %I PMLR %P 6529--6553 %U https://proceedings.mlr.press/v151/li22e.html %V 151 %X Linear contextual bandit is a popular online learning problem. It has been mostly studied in centralized learning settings. With the surging demand of large-scale decentralized model learning, e.g., federated learning, how to retain regret minimization while reducing communication cost becomes an open challenge. In this paper, we study linear contextual bandit in a federated learning setting. We propose a general framework with asynchronous model update and communication for a collection of homogeneous clients and heterogeneous clients, respectively. Rigorous theoretical analysis is provided about the regret and communication cost under this distributed learning framework; and extensive empirical evaluations demonstrate the effectiveness of our solution.
APA
Li, C. & Wang, H.. (2022). Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:6529-6553 Available from https://proceedings.mlr.press/v151/li22e.html.

Related Material