论文标题
多代理性能预测：从全球稳定性和最佳性到混乱
Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos
论文作者
论文摘要
最新的表演预测框架旨在捕获预测会影响他们想要预测的目标/结果的设置。在本文中，我们介绍了该框架的自然多代理版本，其中多个决策者试图预测相同的结果。我们展示了这种竞争可以通过证明从稳定到不稳定和最终混乱的相变可能性，从而导致有趣的现象。具体而言，我们介绍了多代理性能预测的设置，在充分条件下，它们的动态导致了全球稳定性和最佳性。在相反的方向上，当代理商的学习/更新率不太谨慎时，我们表明不稳定和正式的混乱是可能的。我们通过模拟来补充理论预测，以展示结果的预测能力。
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.
