mlsanityData to 7 Oct 2026

Sequential Transfer in Multi-armed Bandit with Finite Set of Models

arXiv 1307.6887 ↗First posted 25 Jul 2013stat.ML cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

Learning from prior tasks and transferring that experience to improve future performance is critical for building lifelong learning agents. Although results in supervised and reinforcement learning show that transfer may significantly improve the learning performance, most of the literature on transfer is focused on batch learning tasks. In this paper we study the problem of textitsequential transfer in online learning, notably in the multi-armed bandit framework, where the objective is to minimize the cumulative regret over a sequence of tasks by incrementally transferring knowledge from prior tasks. We introduce a novel bandit algorithm based on a method-of-moments approach for the estimation of the possible tasks and derive regret bounds for it.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jul 2013.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 15; 2023: 3; 2024: 6; 2025: 5.

38 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. 2022Provable Benefits of Representational Transfer in Reinforcement Learningcited by 38
  4. 2021Hierarchical Bayesian Banditscited by 33
  5. 2021No Regrets for Learning the Prior in Banditscited by 29
  6. 2021Metadata-based Multi-Task Bandits with Bayesian Hierarchical Modelscited by 24
  7. 2022Mixed-Effect Thompson Samplingcited by 14
  8. 2022Non-Stationary Representation Learning in Sequential Linear Banditscited by 13
  9. 2024Theoretical Constraints on the Expressive Power of mathsfRoPE-based Tensor Attention Transformerscited by 12
  10. 2022Modeling Attrition in Recommender Systems with Departing Banditscited by 11
  11. 2022Meta-Learning for Simple Regret Minimizationcited by 10
  12. 2022Multi-Task Off-Policy Learning from Bandit Feedbackcited by 9
26 more
  1. 2022Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Armscited by 8
  2. 2023Meta-Learning Adversarial Bandit Algorithmscited by 8
  3. 2023Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneitycited by 7
  4. 2025Offline-to-online hyperparameter transfer for stochastic banditscited by 6
  5. 2022Meta-Learning Adversarial Banditscited by 5
  6. 2022On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structurecited by 5
  7. 2024Diffusion Models Meet Contextual Banditscited by 5
  8. 2024Causally Abstracted Multi-armed Banditscited by 5
  9. 2025Contextual Thompson Sampling via Generation of Missing Datacited by 5
  10. 2022Meta Learning MDPs with Linear Transition Modelscited by 4
  11. 2022PAC-Bayesian Lifelong Learning For Multi-Armed Banditscited by 4
  12. 2022Multi-Environment Meta-Learning in Stochastic Linear Banditscited by 4
  13. 2024Meta Learning in Bandits within Shared Affine Subspacescited by 4
  14. 2022Hypothesis Transfer in Bandits by Weighted Modelscited by 2
  15. 2024Transfer in Sequential Multi-armed Bandits via Reward Samplescited by 2
  16. 2025Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decodingcited by 2
  17. 2021Transfer Learning in Bandits with Latent Continuitycited by 1
  18. 2022Representation Learning for Context-Dependent Decision-Makingcited by 1
  19. 2022Detection and Evaluation of Clusters within Sequential Datacited by 1
  20. 2025A Classification View on Meta Learning Banditscited by 1
  21. 2021Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodescited by 0
  22. 2021Recommending with Recommendationscited by 0
  23. 2021Chronological Causal Banditscited by 0
  24. 2023Adversarial Online Multi-Task Reinforcement Learningcited by 0
  25. 2024Minimax-optimal trust-aware multi-armed banditscited by 0
  26. 2025Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learningcited by 0