mlsanityData to 14 Oct 2026

Strategic Linear Contextual Bandits

arXiv 2406.00551 ↗First posted 1 Jun 2024cs.LG cs.GTcited by 5

Not on the map. Why?

Abstract (arXiv)

Motivated by the phenomenon of strategic agents gaming a recommender system to maximize the number of times they are recommended to users, we study a strategic variant of the linear contextual bandit problem, where the arms can strategically misreport privately observed contexts to the learner. We treat the algorithm design problem as one of mechanism design under uncertainty and propose the Optimistic Grim Trigger Mechanism (OptGTM) that incentivizes the agents (i.e., arms) to report their contexts truthfully while simultaneously minimizing regret. We also show that failing to account for the strategic nature of the agents results in linear regret. However, a trade-off between mechanism design and regret minimization appears to be unavoidable. More broadly, this work aims to provide insight into the intersection of online learning and mechanism design.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 34 of its 55 references that are in the map. First posted on arXiv 1 Jun 2024.

Builds on

34 of 55 references.

References · 34

  1. 2015Strategic Classificationcited by 257
  2. 2017Strategic Classification from Revealed Preferencescited by 128
  3. 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
  4. 2015Bayesian Incentive-Compatible Bandit Explorationcited by 53
  5. 2022Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptionscited by 51
  6. 2020PAC-Learning for Strategic Classificationcited by 50
  7. 2021A Model Selection Approach for Corruption Robust Reinforcement Learningcited by 45
  8. 2020Efficient and Robust Algorithms for Adversarial Linear Contextual Banditscited by 43
  9. 2022Modeling Content Creator Incentives on Algorithm-Curated Platformscited by 35
  10. 2020Adversarial Attacks on Linear Contextual Banditscited by 34
  11. 2021Robust Stochastic Linear Contextual Bandits Under Adversarial Attackscited by 33
  12. 2022Supply-Side Equilibria in Recommender Systemscited by 33
22 more
  1. 2021Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responsescited by 32
  2. 2023How Bad is Top-K Recommendation under Competing Content Creators?cited by 27
  3. 2021Linear Contextual Bandits with Adversarial Corruptionscited by 21
  4. 2023First- and Second-Order Bounds for Adversarial Linear Contextual Banditscited by 19
  5. 2023Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Banditscited by 19
  6. 2017Multi-armed Bandit Problems with Strategic Armscited by 16
  7. 2019The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulationcited by 15
  8. 2020No-Regret and Incentive-Compatible Online Learningcited by 14
  9. 2023A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systemscited by 13
  10. 2023One-Shot Strategic Classification Under Unknown Costscited by 13
  11. 2024Accounting for AI and Users Shaping One Another: The Role of Mathematical Modelscited by 11
  12. 2023Strategic Apple Tastingcited by 10
  13. 2023Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?cited by 10
  14. 2024User Welfare Optimization in Recommender Systems with Competing Content Creatorscited by 10
  15. 2022Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instrumentscited by 9
  16. 2024Poisoning Attacks against Recommender Systems: A Surveycited by 7
  17. 2013Linear Regression from Strategic Data Sourcescited by 6
  18. 2021Combinatorial Bandits under Strategic Manipulationscited by 6
  19. 2023Incentivizing High-Quality Content in Online Recommender Systemscited by 6
  20. 2023Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendationcited by 6
  21. 2021Multi-armed Bandit Algorithm against Strategic Replicationcited by 5
  22. 2023Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agentscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Strategyproof Reinforcement Learning from Human Feedbackcited by 5
  2. 2025COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agentscited by 1
  3. 2026A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problemscited by 0
  4. 2026Tighter Regret Bounds for Contextual Action-Set Reinforcement Learningcited by 0
  5. 2026MESHA: Mechanism-Enforced Sequential Halving for Strategic Linear Banditscited by 0