Evolutionary Prediction Games

Eden Saig, Nir Rosenfeld

Keywords: Evolutionary Game Theory, Feedback Loops, Stateful Performative Prediction, Potential Games, Replicator Dynamics

TL;DR: We propose a framework based on evolutionary game theory to model feedback loops in supervised learning, and use it to study how different learning settings affect long-term outcomes.

Abstract: When a prediction algorithm serves a collection of users, disparities in prediction quality are likely to emerge. If users respond to accurate predictions by increasing engagement, inviting friends, or adopting trends, repeated learning creates a feedback loop that shapes both the model and the population of its users. In this work, we introduce evolutionary prediction games, a framework grounded in evolutionary game theory which models such feedback loops as natural-selection processes among groups of users. Our theoretical analysis reveals a gap between idealized and real-world learning settings: In idealized settings with unlimited data and computational power, repeated learning creates competition and promotes competitive exclusion across a broad class of behavioral dynamics. However, under realistic constraints such as finite data, limited compute, or risk of overfitting, we show that stable coexistence and mutualistic symbiosis between groups becomes possible. We analyze these possibilities in terms of their stability and feasibility, present mechanisms that can sustain their existence, and empirically demonstrate our findings.

Primary Area: Theory (e.g., control theory, learning theory, algorithmic game theory)

Submission Number: 1323