mlsanityData to 7 Oct 2026

Performative Prediction in a Stateful World

arXiv 2011.03885 ↗First posted 8 Nov 2020cs.LG cs.GTcited by 90

Not on the map. Why?

Abstract (arXiv)

Deployed supervised machine learning models make predictions that interact with and influence the world. This phenomenon is called performative prediction by Perdomo et al. (ICML 2020). It is an ongoing challenge to understand the influence of such predictions as well as design tools so as to control that influence. We propose a theoretical framework where the response of a target population to the deployed classifier is modeled as a function of the classifier and the current state (distribution) of the population. We show necessary and sufficient conditions for convergence to an equilibrium of two retraining algorithms, repeated risk minimization and a lazier variant. Furthermore, convergence is near an optimal classifier. We thus generalize results of Perdomo et al., whose performativity framework does not assume any dependence on the state of the target population. A particular phenomenon captured by our model is that of distinct groups that acquire information and resources at different rates to be able to respond to the latest deployed classifier. We study this phenomenon theoretically and empirically.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 17; 2023: 12; 2024: 17; 2025: 19; 2026: 15.

90 papers.

Sort:

By area:

  1. 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 95
  2. 2021How to Learn when Data Reacts to Your Model: Performative Gradient Descentcited by 70
  3. 2022Data Feedback Loops: Model-driven Amplification of Dataset Biasescited by 59
  4. 2021Strategic Classification Made Practicalcited by 58
  5. 2021Who Leads and Who Follows in Strategic Classification?cited by 53
  6. 2023Performative Prediction: Past and Futurecited by 52
  7. 2021Alternative Microfoundations for Strategic Classificationcited by 47
  8. 2022Multiplayer Performative Prediction: Learning in Decision-Dependent Gamescited by 42
  9. 2022Performative Powercited by 42
  10. 2022Regret Minimization with Performative Feedbackcited by 40
  11. 2022Multi-agent Performative Prediction: From Global Stability and Optimality to Chaoscited by 33
  12. 2023Performative Prediction with Neural Networkscited by 33
38 more
  1. 2022Making Decisions under Outcome Performativitycited by 32
  2. 2022Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environmentscited by 31
  3. 2021How to Learn when Data Gradually Reacts to Your Modelcited by 29
  4. 2022Preference Dynamics Under Personalized Recommendationscited by 25
  5. 2022Performative Reinforcement Learningcited by 25
  6. 2023Plug-in Performative Optimizationcited by 20
  7. 2021Zeroth-Order Methods for Convex-Concave Minmax Problems: Applications to Decision-Dependent Risk Minimizationcited by 18
  8. 2023Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shiftscited by 14
  9. 2024Human Expertise in Algorithmic Predictioncited by 13
  10. 2024Performative Reinforcement Learning in Gradually Shifting Environmentscited by 13
  11. 2022Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimalitycited by 12
  12. 2023Performative Recommendation: Diversifying Content via Strategic Incentivescited by 12
  13. 2021Approximate Regions of Attraction in Learning with Decision-Dependent Distributionscited by 11
  14. 2023Performative Prediction with Bandit Feedback: Learning through Reparameterizationcited by 11
  15. 2024Addressing Polarization and Unfairness in Performative Predictioncited by 11
  16. 2025Revisiting the Predictability of Performative, Social Eventscited by 11
  17. 2023Zero-Regret Performative Prediction Under Inequality Constraintscited by 10
  18. 2021Model Transferability With Responsive Decision Subjectscited by 9
  19. 2022Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instrumentscited by 9
  20. 2023The Risks of Recourse in Binary Classificationcited by 8
  21. 2023Performative Time-Series Forecastingcited by 8
  22. 2024Performative Reinforcement Learning with Linear Markov Decision Processcited by 8
  23. 2024Performative Prediction on Games and Mechanism Designcited by 7
  24. 2024Distributionally Robust Performative Predictioncited by 7
  25. 2022Stochastic Saddle Point Problems with Decision-Dependent Distributionscited by 6
  26. 2022Online Convex Optimization with Unbounded Memorycited by 6
  27. 2024Learning In Reverse Causal Strategic Environments With Ramifications on Two Sided Marketscited by 6
  28. 2024Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairnesscited by 6
  29. 2025A Market for Accuracy: Classification under Competitioncited by 6
  30. 2025On Corruption-Robustness in Performative Reinforcement Learningcited by 6
  31. 2022Emergent specialization from participation dynamics and multi-learner retrainingcited by 5
  32. 2023Algorithmic Censoring in Dynamic Learning Systemscited by 5
  33. 2025Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamicscited by 5
  34. 2025Independent Learning in Performative Markov Potential Gamescited by 5
  35. 2025Generalization Bounds and Stopping Rules for Learning with Self-Selected Datacited by 5
  36. 2022Optimizing the Performative Risk under Weak Convexity Assumptionscited by 4
  37. 2024Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Clipping Bias and Remediescited by 4
  38. 2024The Limitations of Model Retraining in the Face of Performativitycited by 4

50 most cited of 90 All 90 (JSON)