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

TL;DR

This paper extends performative prediction to a multi-agent setting, revealing how competition among agents can lead to stable, optimal outcomes or chaotic dynamics depending on their caution levels.

Contribution

It introduces a multi-agent performative prediction framework and analyzes conditions leading to stability, optimality, or chaos in the agents' dynamics.

Findings

Phase transitions from stability to chaos in multi-agent dynamics

Conditions for global stability and optimality

Potential for chaos with less cautious agents

Abstract

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.