mlsanityData to 7 Oct 2026

Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos

arXiv 2201.10483 ↗First posted 25 Jan 2022cs.LG cs.GT cs.SYcited by 33

Not on the map. Why?

Abstract (arXiv)

The recent framework of performative prediction is aimed at capturing settings where predictions influence the target/outcome they want to predict. In this paper, we introduce a natural multi-agent version of this framework, where multiple decision makers try to predict the same outcome. We showcase that such competition can result in interesting phenomena by proving the possibility of phase transitions from stability to instability and eventually chaos. Specifically, we present settings of multi-agent performative prediction where under sufficient conditions their dynamics lead to global stability and optimality. In the opposite direction, when the agents are not sufficiently cautious in their learning/updates rates, we show that instability and in fact formal chaos is possible. We complement our theoretical predictions with simulations showcasing the predictive power of our results.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 30 of its 63 references that are in the map. First posted on arXiv 25 Jan 2022.

Builds on

30 of 63 references.

References · 30

  1. 2020Performative Predictioncited by 318
  2. 2015Strategic Classificationcited by 256
  3. 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 95
  4. 2020Stochastic Optimization for Performative Predictioncited by 92
  5. 2020Performative Prediction in a Stateful Worldcited by 90
  6. 2021How to Learn when Data Reacts to Your Model: Performative Gradient Descentcited by 70
  7. 2020Stochastic optimization with decision-dependent distributionscited by 65
  8. 2020No-regret learning and mixed Nash equilibria: They do not mixcited by 49
  9. 2022Multiplayer Performative Prediction: Learning in Decision-Dependent Gamescited by 42
  10. 2017Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaoscited by 29
  11. 2021Survival of the strictest: Stable and unstable equilibria under regularized learning with partial informationcited by 22
  12. 2020On the Impossibility of Global Convergence in Multi-Loss Optimizationcited by 16
18 more
  1. 2020Chaos, Extremism and Optimism: Volume Analysis of Learning in Gamescited by 16
  2. 2019The route to chaos in routing games: When is Price of Anarchy too optimistic?cited by 14
  3. 2021Learning in Matrix Games can be Arbitrarily Complexcited by 11
  4. 2021Follow-the-Regularized-Leader Routes to Chaos in Routing Gamescited by 9
  5. 2020Chaos of Learning Beyond Zero-sum and Coordination via Game Decompositionscited by 8
  6. 2020Learning and Strongly Truthful Multi-Task Peer Prediction: A Variational Approachcited by 8
  7. 2018Multiplicative Weights Update as a Distributed Constrained Optimization Algorithm: Convergence to Second-order Stationary Points Almost Alwayscited by 7
  8. 2020Smooth markets: A basic mechanism for organizing gradient-based learnerscited by 4
  9. 2021The Limits of Multi-task Peer Predictioncited by 4
  10. 2021Optimal Scoring Rule Design under Partial Knowledgecited by 4
  11. 2020Limitations of Greed: Influence Maximization in Undirected Networks Re-visitedcited by 3
  12. 2021Dynamical Analysis of the EIP-1559 Ethereum Fee Marketcited by 3
  13. 2021Subspace Differential Privacycited by 3
  14. 2021Learning in Markets: Greed Leads to Chaos but Following the Price is Rightcited by 2
  15. 2021Cooperation in Threshold Public Projects with Binary Actionscited by 2
  16. 2020Think Globally, Act Locally: On the Optimal Seeding for Nonsubmodular Influence Maximizationcited by 1
  17. 2020Timely Information from Prediction Marketscited by 1
  18. 2021Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signaturescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 8; 2025: 5; 2026: 10.

33 papers.

Sort:

By area:

  1. 2023Performative Prediction: Past and Futurecited by 52
  2. 2022Performative Powercited by 42
  3. 2022Anticipating Performativity by Predicting from Predictionscited by 37
  4. 2023Plug-in Performative Optimizationcited by 20
  5. 2022Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimalitycited by 12
  6. 2023Performative Prediction with Bandit Feedback: Learning through Reparameterizationcited by 11
  7. 2023Zero-Regret Performative Prediction Under Inequality Constraintscited by 10
  8. 2023Designing Long-term Group Fair Policies in Dynamical Systemscited by 8
  9. 2024Performative Reinforcement Learning with Linear Markov Decision Processcited by 8
  10. 2024The Good, the Bad, and the Hulk-like GPT: Analyzing Emotional Decisions of Large Language Models in Cooperation and Bargaining Gamescited by 7
  11. 2024Performative Prediction on Games and Mechanism Designcited by 7
  12. 2025On Corruption-Robustness in Performative Reinforcement Learningcited by 6
21 more
  1. 2022Emergent specialization from participation dynamics and multi-learner retrainingcited by 5
  2. 2025Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamicscited by 5
  3. 2025Independent Learning in Performative Markov Potential Gamescited by 5
  4. 2025Performative Policy Gradient: Optimality in Performative Reinforcement Learningcited by 4
  5. 2026The Stability of Online Algorithms in Performative Predictioncited by 4
  6. 2024Strategic Usage in a Multi-Learner Settingcited by 3
  7. 2024Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streamscited by 3
  8. 2024Learning from Streaming Data when Users Choosecited by 2
  9. 2026On the Computational Complexity of Performative Predictioncited by 2
  10. 2026Dissecting Performative Prediction: A Comprehensive Surveycited by 2
  11. 2024Tracking solutions of time-varying variational inequalitiescited by 1
  12. 2024Swim till You Sink: Computing the Limit of a Gamecited by 1
  13. 2026Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loopcited by 1
  14. 2023Chaos persists in large-scale multi-agent learning despite adaptive learning ratescited by 0
  15. 2025On multiagent online problems with predictionscited by 0
  16. 2026When Predictions Shape Reality: A Socio-Technical Synthesis of Performative Predictions in Machine Learningcited by 0
  17. 2026When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loopcited by 0
  18. 2026Natural Invariant Measures for Chaotic Game Dynamics: Finding Order in Chaoscited by 0
  19. 2026Local and Global Stability in Performative Reinforcement Learningcited by 0
  20. 2026Stabilizing Performative Feedback Loops with Minimal Model Deploymentscited by 0
  21. 2026When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worldscited by 0