Cella, L; Lazaric, A; Pontil, M; (2020) Meta-learning with Stochastic Linear Bandits. In: Daumé III, H and Singh, A, (eds.) Proceedings of the 37th International Conference on Machine Learning. (pp. pp. 1337-1347). Proceedings of Machine Learning Research (PMLR): Virtual conference.

Preview

Text cella20a.pdf - Published Version Download (807kB) | Preview

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.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item