mlsanityData to 7 Oct 2026

Meta Learning in Bandits within Shared Affine Subspaces

arXiv 2404.00688 ↗First posted 31 Mar 2024cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

We study the problem of meta-learning several contextual stochastic bandits tasks by leveraging their concentration around a low-dimensional affine subspace, which we learn via online principal component analysis to reduce the expected regret over the encountered bandits. We propose and theoretically analyze two strategies that solve the problem: One based on the principle of optimism in the face of uncertainty and the other via Thompson sampling. Our framework is generic and includes previously proposed approaches as special cases. Besides, the empirical results show that our methods significantly reduce the regret on several bandit tasks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 48 references that are in the map. First posted on arXiv 31 Mar 2024.

Builds on

22 of 48 references.

References · 22

  1. 2017A Tutorial on Thompson Samplingcited by 420
  2. 2019Online Meta-Learningcited by 137
  3. 2020PACOH: Bayes-Optimal Meta-Learning with PAC-Guaranteescited by 85
  4. 2017Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theorycited by 76
  5. 2021Meta-Thompson Samplingcited by 62
  6. 2020Impact of Representation Learning in Linear Banditscited by 51
  7. 2020Meta-learning with Stochastic Linear Banditscited by 45
  8. 2019Meta Dynamic Pricing: Transfer Learning Across Experimentscited by 41
  9. 2013Sequential Transfer in Multi-armed Bandit with Finite Set of Modelscited by 38
  10. 2021No Regrets for Learning the Prior in Banditscited by 29
  11. 2022Multi-task Representation Learning with Stochastic Linear Banditscited by 20
  12. 2019Laplacian-regularized graph bandits: Algorithms and theoretical analysiscited by 17
10 more
  1. 2021Metalearning Linear Bandits by Prior Updatecited by 15
  2. 2015Online Principal Component Analysis in High Dimension: Which Algorithm to Choose?cited by 12
  3. 2022Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Armscited by 8
  4. 2022Meta Representation Learning with Contextual Linear Banditscited by 6
  5. 2020Differentiable Linear Bandit Algorithmcited by 5
  6. 2022Meta-Learning Hypothesis Spaces for Sequential Decision-makingcited by 5
  7. 2022Meta-Learning Adversarial Banditscited by 5
  8. 2022Linear Combinatorial Semi-Bandit with Causally Related Rewardscited by 4
  9. 2022Lifelong Bandit Optimization: No Prior and No Regretcited by 3
  10. 2022Hypothesis Transfer in Bandits by Weighted Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Understanding Optimal Feature Transfer via a Fine-Grained Bias-Variance Analysiscited by 2
  2. 2025Beyond Task Diversity: Provable Representation Transfer for Sequential Multi-Task Linear Banditscited by 1
  3. 2026Invariance-Based Dynamic Regret Minimizationcited by 0
  4. 2026Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Banditscited by 0