Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing

When users choose among competing models, each model’s training data depends on its current behavior. We characterize how this feedback loop can drive overspecialization and introduce peer-model probing, a method for diagnosing information hidden by user sorting. The project connects strategic user choice with decision-dependent learning in deployed ML systems.

I led the project end to end, including problem formulation, theoretical and experimental development, writing, and coordination, with guidance and feedback from my collaborators. The paper was accepted to UAI 2026.