Meta-learning with Stochastic Linear Bandits

Leonardo Cella, Alessandro Lazaric, Massimiliano Pontil
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:1360-1370, 2020.

Abstract

We investigate meta-learning procedures in the setting of stochastic linear bandits tasks. The goal is to select a learning algorithm which works well on average over a class of bandits tasks, that are sampled from a task-distribution. Inspired by recent work on learning-to-learn linear regression, we consider a class of bandit algorithms that implement a regularized version of the well-known OFUL algorithm, where the regularization is a square euclidean distance to a bias vector. We first study the benefit of the biased OFUL algorithm in terms of regret minimization. We then propose two strategies to estimate the bias within the learning-to-learn setting. We show both theoretically and experimentally, that when the number of tasks grows and the variance of the task-distribution is small, our strategies have a significant advantage over learning the tasks in isolation.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-cella20a, title = {Meta-learning with Stochastic Linear Bandits}, author = {Cella, Leonardo and Lazaric, Alessandro and Pontil, Massimiliano}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {1360--1370}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/cella20a/cella20a.pdf}, url = {http://proceedings.mlr.press/v119/cella20a.html}, abstract = {We investigate meta-learning procedures in the setting of stochastic linear bandits tasks. The goal is to select a learning algorithm which works well on average over a class of bandits tasks, that are sampled from a task-distribution. Inspired by recent work on learning-to-learn linear regression, we consider a class of bandit algorithms that implement a regularized version of the well-known OFUL algorithm, where the regularization is a square euclidean distance to a bias vector. We first study the benefit of the biased OFUL algorithm in terms of regret minimization. We then propose two strategies to estimate the bias within the learning-to-learn setting. We show both theoretically and experimentally, that when the number of tasks grows and the variance of the task-distribution is small, our strategies have a significant advantage over learning the tasks in isolation.} }
Endnote
%0 Conference Paper %T Meta-learning with Stochastic Linear Bandits %A Leonardo Cella %A Alessandro Lazaric %A Massimiliano Pontil %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-cella20a %I PMLR %P 1360--1370 %U http://proceedings.mlr.press/v119/cella20a.html %V 119 %X We investigate meta-learning procedures in the setting of stochastic linear bandits tasks. The goal is to select a learning algorithm which works well on average over a class of bandits tasks, that are sampled from a task-distribution. Inspired by recent work on learning-to-learn linear regression, we consider a class of bandit algorithms that implement a regularized version of the well-known OFUL algorithm, where the regularization is a square euclidean distance to a bias vector. We first study the benefit of the biased OFUL algorithm in terms of regret minimization. We then propose two strategies to estimate the bias within the learning-to-learn setting. We show both theoretically and experimentally, that when the number of tasks grows and the variance of the task-distribution is small, our strategies have a significant advantage over learning the tasks in isolation.
APA
Cella, L., Lazaric, A. & Pontil, M.. (2020). Meta-learning with Stochastic Linear Bandits. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:1360-1370 Available from http://proceedings.mlr.press/v119/cella20a.html.

Related Material