mlsanityData to 7 Oct 2026

Meta-learning with Stochastic Linear Bandits

arXiv 2005.08531 ↗First posted 18 May 2020stat.ML cs.LGcited by 45

Not on the map. Why?

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.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 15; 2023: 5; 2024: 6; 2025: 6; 2026: 1.

45 papers.

Sort:

By area:

  1. 2021Meta-Thompson Samplingcited by 62
  2. 2021Bayesian decision-making under misspecified priors with applications to meta-learningcited by 43
  3. 2021Hierarchical Bayesian Banditscited by 33
  4. 2021No Regrets for Learning the Prior in Banditscited by 29
  5. 2021Metadata-based Multi-Task Bandits with Bayesian Hierarchical Modelscited by 24
  6. 2022Multi-task Representation Learning with Stochastic Linear Banditscited by 20
  7. 2021Metalearning Linear Bandits by Prior Updatecited by 15
  8. 2022Mixed-Effect Thompson Samplingcited by 14
  9. 2022Non-Stationary Representation Learning in Sequential Linear Banditscited by 13
  10. 2023Online Clustering of Bandits with Misspecified User Modelscited by 12
  11. 2021Multitask Learning and Bandits via Robust Statisticscited by 11
  12. 2021Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridgecited by 10
33 more
  1. 2022Meta-Learning for Simple Regret Minimizationcited by 10
  2. 2022Multi-Task Off-Policy Learning from Bandit Feedbackcited by 9
  3. 2022Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Armscited by 8
  4. 2023Meta-Learning Adversarial Bandit Algorithmscited by 8
  5. 2023Thompson Sampling with Diffusion Generative Priorcited by 7
  6. 2023Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneitycited by 7
  7. 2022Meta Representation Learning with Contextual Linear Banditscited by 6
  8. 2021Feature and Parameter Selection in Stochastic Linear Banditscited by 5
  9. 2022Meta-Learning Hypothesis Spaces for Sequential Decision-makingcited by 5
  10. 2022Meta-Learning Adversarial Banditscited by 5
  11. 2022On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structurecited by 5
  12. 2024Diffusion Models Meet Contextual Banditscited by 5
  13. 2025Contextual Thompson Sampling via Generation of Missing Datacited by 5
  14. 2022Meta Learning MDPs with Linear Transition Modelscited by 4
  15. 2022Multi-Environment Meta-Learning in Stochastic Linear Banditscited by 4
  16. 2024Meta Learning in Bandits within Shared Affine Subspacescited by 4
  17. 2022Lifelong Bandit Optimization: No Prior and No Regretcited by 3
  18. 2023Context-lumpable stochastic banditscited by 3
  19. 2022Online Meta-Learning in Adversarial Multi-Armed Banditscited by 2
  20. 2024Transfer in Sequential Multi-armed Bandits via Reward Samplescited by 2
  21. 2021Transfer Learning in Bandits with Latent Continuitycited by 1
  22. 2024Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneitycited by 1
  23. 2024Exploiting Adjacent Similarity in Multi-Armed Bandit Tasks via Transfer of Reward Samplescited by 1
  24. 2025A Classification View on Meta Learning Banditscited by 1
  25. 2021Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodescited by 0
  26. 2021Recommending with Recommendationscited by 0
  27. 2022POMRL: No-Regret Learning-to-Plan with Increasing Horizonscited by 0
  28. 2024Minimax-optimal trust-aware multi-armed banditscited by 0
  29. 2025Representative Action Selection for Large Action Space Bandit Familiescited by 0
  30. 2025Secure Best Arm Identification in the Presence of a Copycatcited by 0
  31. 2025Empirical Bayesian Multi-Bandit Learningcited by 0
  32. 2025Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Banditscited by 0
  33. 2026Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Banditscited by 0