mlsanityData to 14 Oct 2026

Causally Abstracted Multi-armed Bandits

arXiv 2404.17493 ↗First posted 26 Apr 2024cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Multi-armed bandits (MAB) and causal MABs (CMAB) are established frameworks for decision-making problems. The majority of prior work typically studies and solves individual MAB and CMAB in isolation for a given problem and associated data. However, decision-makers are often faced with multiple related problems and multi-scale observations where joint formulations are needed in order to efficiently exploit the problem structures and data dependencies. Transfer learning for CMABs addresses the situation where models are defined on identical variables, although causal connections may differ. In this work, we extend transfer learning to setups involving CMABs defined on potentially different variables, with varying degrees of granularity, and related via an abstraction map. Formally, we introduce the problem of causally abstracted MABs (CAMABs) by relying on the theory of causal abstraction in order to express a rigorous abstraction map. We propose algorithms to learn in a CAMAB, and study their regret. We illustrate the limitations and the strengths of our algorithms on a real-world scenario related to online advertising.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 26 Apr 2024.

Builds on

33 of 59 references.

References · 33

  1. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  2. 2014Learning to Optimize via Information-Directed Samplingcited by 168
  3. 2017Causal Consistency of Structural Equation Modelscited by 118
  4. 2018Abstracting Causal Modelscited by 107
  5. 2016Causal Bandits: Learning Good Interventions via Causal Inferencecited by 101
  6. 2019Weighted Linear Bandits for Non-Stationary Environmentscited by 86
  7. 2013Bandits and Experts in Metric Spacescited by 63
  8. 2019Approximate Causal Abstractioncited by 63
  9. 2014Lipschitz Bandits: Regret Lower Bounds and Optimal Algorithmscited by 60
  10. 2019Nearly Minimax-Optimal Regret for Linearly Parameterized Banditscited by 54
  11. 2021A Simple Approach for Non-stationary Linear Banditscited by 54
  12. 2016The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Banditscited by 49
21 more
  1. 2017Minimal Exploration in Structured Stochastic Banditscited by 41
  2. 2020Causal Bayesian Optimizationcited by 39
  3. 2013Sequential Transfer in Multi-armed Bandit with Finite Set of Modelscited by 38
  4. 2020Budgeted and Non-budgeted Causal Banditscited by 38
  5. 2022Causal Effect Identification in Cluster DAGscited by 36
  6. 2019Multi-Armed Bandits with Correlated Armscited by 34
  7. 2021Compositional Abstraction Error and a Category of Causal Modelscited by 33
  8. 2023Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributionscited by 23
  9. 2024Neural Causal Abstractionscited by 21
  10. 2022Adaptively Exploiting d-Separators with Causal Banditscited by 18
  11. 2022Combinatorial Causal Banditscited by 16
  12. 2014Bounded Regret for Finite-Armed Structured Banditscited by 15
  13. 2022Abstraction between Structural Causal Models: A Review of Definitions and Propertiescited by 15
  14. 2020Optimal Learning for Structured Banditscited by 14
  15. 2020Multi-task Causal Learning with Gaussian Processescited by 14
  16. 2023Causal Optimal Transport of Abstractionscited by 13
  17. 2020Multi-Armed Bandits with Dependent Armscited by 12
  18. 2020On conditional versus marginal bias in multi-armed banditscited by 9
  19. 2023Quantifying Consistency and Information Loss for Causal Abstraction Learningcited by 7
  20. 2018Regional Multi-Armed Banditscited by 6
  21. 2023Interventionally Consistent Surrogates for Agent-based Simulatorscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2024Aligning Graphical and Functional Causal Abstractionscited by 6
  2. 2025What is causal about causal models and representations?cited by 6
  3. 2025Distributionally Robust Causal Abstractionscited by 3
  4. 2025Identifiability in Causal Abstractions: A Hierarchy of Criteriacited by 2
  5. 2025Using causal abstractions to accelerate decision-making in complex bandit problemscited by 1
  6. 2026Causal Effect Identifiability in Causal Abstractions: A Strict Hierarchy of Criteriacited by 0