Partially Performative Prediction
For machine learning practitioners deploying models in dynamic real-world settings, this work provides a more realistic model of distribution shift that accounts for both model-induced and external changes.
This paper introduces partially performative prediction, a framework that models distribution shift as a combination of endogenous shifts caused by model deployment and exogenous shifts from external time-varying processes. The authors extend performative stability and optimality to online settings and analyze when repeated retraining successfully adapts to such environments.
Performative prediction studies feedback loops that arise when predictive models are deployed in consequential domains. In these settings, deploying a model can change the population whose patterns the model aims to predict, inducing a distribution shift that is endogenous to the learning system. This perspective departs from classical treatments of distribution shift, where shifts are typically modeled as exogenous changes in the data-generating process. Yet, in practice, distribution shift is rarely one or the other. Predictive models may influence future data through the decisions they support, while the world itself continues to drift for reasons beyond the learner's control. We study partially performative prediction, a framework that captures both endogenous and exogenous sources of distribution shift. The framework generalizes performative prediction by allowing the data distribution to evolve both in response to the deployed model and according to an external, time-varying process. We extend the central notions of performative stability and performative optimality to this setting by defining their online analogues that track the evolving partially performative environment. We analyze practical learning heuristics, including repeated retraining, and characterize when they successfully adapt to partially performative environments.