# Meta-learning with Stochastic Linear Bandits

arXiv: https://arxiv.org/abs/2005.08531 · HTML: https://mlsanity.com/paper/2005.08531/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2020.

## Built on by (most cited first, 30 of 46)

- [Meta-Thompson Sampling](https://mlsanity.com/paper/2102.06129/) (2021)
- [Bayesian decision-making under misspecified priors with applications to meta-learning](https://mlsanity.com/paper/2107.01509/) (2021)
- [Hierarchical Bayesian Bandits](https://mlsanity.com/paper/2111.06929/) (2021)
- [No Regrets for Learning the Prior in Bandits](https://mlsanity.com/paper/2107.06196/) (2021)
- [Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models](https://mlsanity.com/paper/2108.06422/) (2021)
- [Multi-task Representation Learning with Stochastic Linear Bandits](https://mlsanity.com/paper/2202.10066/) (2022)
- [Metalearning Linear Bandits by Prior Update](https://mlsanity.com/paper/2107.05320/) (2021)
- [Mixed-Effect Thompson Sampling](https://mlsanity.com/paper/2205.15124/) (2022)
- [Non-Stationary Representation Learning in Sequential Linear Bandits](https://mlsanity.com/paper/2201.04805/) (2022)
- [Online Clustering of Bandits with Misspecified User Models](https://mlsanity.com/paper/2310.02717/) (2023)
- [Multitask Learning and Bandits via Robust Statistics](https://mlsanity.com/paper/2112.14233/) (2021)
- [Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge](https://mlsanity.com/paper/2111.01602/) (2021)
- [Meta-Learning for Simple Regret Minimization](https://mlsanity.com/paper/2202.12888/) (2022)
- [Multi-Task Off-Policy Learning from Bandit Feedback](https://mlsanity.com/paper/2212.04720/) (2022)
- [Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms](https://mlsanity.com/paper/2202.13001/) (2022)
- [Meta-Learning Adversarial Bandit Algorithms](https://mlsanity.com/paper/2307.02295/) (2023)
- [Thompson Sampling with Diffusion Generative Prior](https://mlsanity.com/paper/2301.05182/) (2023)
- [Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity](https://mlsanity.com/paper/2306.06291/) (2023)
- [Meta Representation Learning with Contextual Linear Bandits](https://mlsanity.com/paper/2205.15100/) (2022)
- [Contextual Thompson Sampling via Generation of Missing Data](https://mlsanity.com/paper/2502.07064/) (2025)
- [Feature and Parameter Selection in Stochastic Linear Bandits](https://mlsanity.com/paper/2106.05378/) (2021)
- [Meta-Learning Hypothesis Spaces for Sequential Decision-making](https://mlsanity.com/paper/2202.00602/) (2022)
- [Meta-Learning Adversarial Bandits](https://mlsanity.com/paper/2205.14128/) (2022)
- [On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure](https://mlsanity.com/paper/2211.15129/) (2022)
- [Diffusion Models Meet Contextual Bandits](https://mlsanity.com/paper/2402.10028/) (2024)
- [Meta Learning MDPs with Linear Transition Models](https://mlsanity.com/paper/2201.08732/) (2022)
- [Multi-Environment Meta-Learning in Stochastic Linear Bandits](https://mlsanity.com/paper/2205.06326/) (2022)
- [Lifelong Bandit Optimization: No Prior and No Regret](https://mlsanity.com/paper/2210.15513/) (2022)
- [Context-lumpable stochastic bandits](https://mlsanity.com/paper/2306.13053/) (2023)
- [Meta Learning in Bandits within Shared Affine Subspaces](https://mlsanity.com/paper/2404.00688/) (2024)

## Abstract (arXiv)

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.