Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos
This work addresses the challenge of multi-agent interactions in predictive systems for researchers in machine learning and game theory, presenting a novel extension of performative prediction with potential implications for stability in competitive environments.
The paper tackles the problem of multiple decision makers predicting the same outcome in a performative prediction setting, where predictions influence outcomes, and shows that competition can lead to global stability and optimality under certain conditions, but instability and chaos when agents are not cautious, with simulations validating these theoretical predictions.
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.