mlsanityData to 7 Oct 2026

Who Leads and Who Follows in Strategic Classification?

arXiv 2106.12529 ↗First posted 23 Jun 2021cs.LG cs.GTcited by 53

Not on the map. Why?

Abstract (arXiv)

As predictive models are deployed into the real world, they must increasingly contend with strategic behavior. A growing body of work on strategic classification treats this problem as a Stackelberg game: the decision-maker "leads" in the game by deploying a model, and the strategic agents "follow" by playing their best response to the deployed model. Importantly, in this framing, the burden of learning is placed solely on the decision-maker, while the agents' best responses are implicitly treated as instantaneous. In this work, we argue that the order of play in strategic classification is fundamentally determined by the relative frequencies at which the decision-maker and the agents adapt to each other's actions. In particular, by generalizing the standard model to allow both players to learn over time, we show that a decision-maker that makes updates faster than the agents can reverse the order of play, meaning that the agents lead and the decision-maker follows. We observe in standard learning settings that such a role reversal can be desirable for both the decision-maker and the strategic agents. Finally, we show that a decision-maker with the freedom to choose their update frequency can induce learning dynamics that converge to Stackelberg equilibria with either order of play.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 21 of its 52 references that are in the map. First posted on arXiv 23 Jun 2021.

Builds on

21 of 52 references.

References · 21

  1. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 526
  2. 2020Performative Predictioncited by 318
  3. 2015Strategic Classificationcited by 256
  4. 2017Strategic Classification from Revealed Preferencescited by 126
  5. 2018The Social Cost of Strategic Classificationcited by 105
  6. 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 95
  7. 2019Strategic Classification is Causal Modeling in Disguisecited by 92
  8. 2020Stochastic Optimization for Performative Predictioncited by 92
  9. 2020Performative Prediction in a Stateful Worldcited by 90
  10. 2018How Do Classifiers Induce Agents To Invest Effort Strategically?cited by 82
  11. 2018The Disparate Effects of Strategic Manipulationcited by 75
  12. 2021How to Learn when Data Reacts to Your Model: Performative Gradient Descentcited by 70
9 more
  1. 2021Strategic Classification in the Darkcited by 66
  2. 2020Causal Strategic Linear Regressioncited by 65
  3. 2016Kernel-based methods for bandit convex optimizationcited by 63
  4. 2021Strategic Classification Made Practicalcited by 58
  5. 2020The Strategic Perceptroncited by 48
  6. 2018On Gradient-Based Learning in Continuous Gamescited by 46
  7. 2020Maximizing Welfare with Incentive-Aware Evaluation Mechanismscited by 46
  8. 2020The Role of Randomness and Noise in Strategic Classificationcited by 40
  9. 2018Bandit learning in concave N-person gamescited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 14; 2024: 9; 2025: 12; 2026: 7.

53 papers.

Sort:

By area:

  1. 2022Performative Powercited by 42
  2. 2022Regret Minimization with Performative Feedbackcited by 40
  3. 2022The Sample Complexity of Online Contract Designcited by 35
  4. 2022Generalized Strategic Classification and the Case of Aligned Incentivescited by 34
  5. 2023Algorithmic Collective Action in Machine Learningcited by 30
  6. 2023Causal Strategic Classification: A Tale of Two Shiftscited by 30
  7. 2021How to Learn when Data Gradually Reacts to Your Modelcited by 29
  8. 2023Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agentscited by 25
  9. 2022ISAACS: Iterative Soft Adversarial Actor-Critic for Safetycited by 24
  10. 2023Strategic Classification under Unknown Personalized Manipulationcited by 23
  11. 2023Plug-in Performative Optimizationcited by 20
  12. 2023Fundamental Bounds on Online Strategic Classificationcited by 17
38 more
  1. 2022Strategic Classification with Graph Neural Networkscited by 14
  2. 2023Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shiftscited by 14
  3. 2022Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instrumentscited by 9
  4. 2022Diversified Recommendations for Agents with Adaptive Preferencescited by 9
  5. 2023Online Learning in a Creator Economycited by 8
  6. 2025Performative Validity of Recourse Explanationscited by 8
  7. 2023Incentivizing High-Quality Content in Online Recommender Systemscited by 6
  8. 2024Learning In Reverse Causal Strategic Environments With Ramifications on Two Sided Marketscited by 6
  9. 2025Statistical Collusion by Collectives on Learning Platformscited by 6
  10. 2025PAC Learning with Improvementscited by 6
  11. 2023Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flowscited by 5
  12. 2024Impact of Decentralized Learning on Player Utilities in Stackelberg Gamescited by 5
  13. 2024Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactionscited by 5
  14. 2024MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safetycited by 5
  15. 2025Should Decision-Makers Reveal Classifiers in Online Strategic Classification?cited by 5
  16. 2022Strategic Representationcited by 4
  17. 2025Strategic Classification with Non-Linear Classifierscited by 4
  18. 2024Strategic Usage in a Multi-Learner Settingcited by 3
  19. 2024Understanding Model Selection For Learning In Strategic Environmentscited by 3
  20. 2025Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causalitycited by 3
  21. 2024Parameter-Free Algorithms for Performative Regret Minimization under Decision-Dependent Distributionscited by 2
  22. 2024Microfoundation Inference for Strategic Predictioncited by 2
  23. 2025To Give or Not to Give? The Impacts of Strategically Withheld Recoursecited by 2
  24. 2025Conservative classifiers do consistently well with improving agents: characterizing statistical and online learningcited by 2
  25. 2025Look-Ahead Reasoning on Learning Platformscited by 2
  26. 2026On the Computational Complexity of Performative Predictioncited by 2
  27. 2023Stackelberg Batch Policy Learningcited by 1
  28. 2024Online Stackelberg Optimization via Nonlinear Controlcited by 1
  29. 2025Collective dynamics of strategic classificationcited by 1
  30. 2025The Burden of Interactive Alignment with Inconsistent Preferencescited by 1
  31. 2026Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamicscited by 1
  32. 2026Beyond Rational Illusion: Behaviorally Realistic Strategic Classificationcited by 1
  33. 2022A Note on Zeroth-Order Optimization on the Simplexcited by 0
  34. 2023Uncoupled Learning of Differential Stackelberg Equilibria with Commitmentscited by 0
  35. 2023A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learningcited by 0
  36. 2023Strategic Evaluation: Subjects, Evaluators, and Societycited by 0
  37. 2025Last-iterate Convergence for Symmetric, General-sum, 2 × 2 Games Under The Exponential Weights Dynamiccited by 0
  38. 2026Sequential Strategic Classification with Multi-Stage Selective Classifierscited by 0

50 most cited of 53 All 53 (JSON)