mlsanityData to 7 Oct 2026

Stochastic Optimization for Performative Prediction

arXiv 2006.06887 ↗First posted 12 Jun 2020cs.LG cs.GT stat.MLcited by 92

Not on the map. Why?

Abstract (arXiv)

In performative prediction, the choice of a model influences the distribution of future data, typically through actions taken based on the model's predictions. We initiate the study of stochastic optimization for performative prediction. What sets this setting apart from traditional stochastic optimization is the difference between merely updating model parameters and deploying the new model. The latter triggers a shift in the distribution that affects future data, while the former keeps the distribution as is. Assuming smoothness and strong convexity, we prove rates of convergence for both greedily deploying models after each stochastic update (greedy deploy) as well as for taking several updates before redeploying (lazy deploy). In both cases, our bounds smoothly recover the optimal O(1/k) rate as the strength of performativity decreases. Furthermore, they illustrate how depending on the strength of performative effects, there exists a regime where either approach outperforms the other. We experimentally explore the trade-off on both synthetic data and a strategic classification simulator.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 20; 2023: 10; 2024: 21; 2025: 17; 2026: 12.

92 papers.

Sort:

By area:

  1. 2022Online Decision Transformercited by 194
  2. 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 95
  3. 2021How to Learn when Data Reacts to Your Model: Performative Gradient Descentcited by 70
  4. 2021Who Leads and Who Follows in Strategic Classification?cited by 53
  5. 2023Performative Prediction: Past and Futurecited by 52
  6. 2021Alternative Microfoundations for Strategic Classificationcited by 47
  7. 2022Multiplayer Performative Prediction: Learning in Decision-Dependent Gamescited by 42
  8. 2022Performative Powercited by 42
  9. 2022Regret Minimization with Performative Feedbackcited by 40
  10. 2022Anticipating Performativity by Predicting from Predictionscited by 37
  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. 2021Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responsescited by 32
  2. 2022Making Decisions under Outcome Performativitycited by 32
  3. 2022Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environmentscited by 31
  4. 2022A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithmscited by 30
  5. 2021How to Learn when Data Gradually Reacts to Your Modelcited by 29
  6. 2022Performative Reinforcement Learningcited by 25
  7. 2023Plug-in Performative Optimizationcited by 20
  8. 2021Zeroth-Order Methods for Convex-Concave Minmax Problems: Applications to Decision-Dependent Risk Minimizationcited by 18
  9. 2023Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shiftscited by 14
  10. 2021Stochastic Optimization under Distributional Driftcited by 13
  11. 2024Human Expertise in Algorithmic Predictioncited by 13
  12. 2024Performative Reinforcement Learning in Gradually Shifting Environmentscited by 13
  13. 2022Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimalitycited by 12
  14. 2023Performative Recommendation: Diversifying Content via Strategic Incentivescited by 12
  15. 2021Approximate Regions of Attraction in Learning with Decision-Dependent Distributionscited by 11
  16. 2023Performative Prediction with Bandit Feedback: Learning through Reparameterizationcited by 11
  17. 2024Addressing Polarization and Unfairness in Performative Predictioncited by 11
  18. 2025Revisiting the Predictability of Performative, Social Eventscited by 11
  19. 2023Zero-Regret Performative Prediction Under Inequality Constraintscited by 10
  20. 2021Model Transferability With Responsive Decision Subjectscited by 9
  21. 2022Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instrumentscited by 9
  22. 2022Diversified Recommendations for Agents with Adaptive Preferencescited by 9
  23. 2023Incentivizing honest performative predictions with proper scoring rulescited by 9
  24. 2023Performative Time-Series Forecastingcited by 8
  25. 2024Performative Reinforcement Learning with Linear Markov Decision Processcited by 8
  26. 2025Performative Validity of Recourse Explanationscited by 8
  27. 2023Online covariance estimation for stochastic gradient descent under Markovian samplingcited by 7
  28. 2024Distributionally Robust Performative Predictioncited by 7
  29. 2022Stochastic Saddle Point Problems with Decision-Dependent Distributionscited by 6
  30. 2022Constrained Stochastic Nonconvex Optimization with State-dependent Markov Datacited by 6
  31. 2022Online Convex Optimization with Unbounded Memorycited by 6
  32. 2024Learning In Reverse Causal Strategic Environments With Ramifications on Two Sided Marketscited by 6
  33. 2024Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairnesscited by 6
  34. 2025A Statistical Case Against Empirical Human-AI Alignmentcited by 6
  35. 2025On Corruption-Robustness in Performative Reinforcement Learningcited by 6
  36. 2022Emergent specialization from participation dynamics and multi-learner retrainingcited by 5
  37. 2025Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamicscited by 5
  38. 2022Theoretical analysis of Adam using hyperparameters close to one without Lipschitz smoothnesscited by 4

50 most cited of 92 All 92 (JSON)