Strategic Classification Made Practical
It addresses the gap between theoretical work and practical application in strategic classification, making it more usable for real-world scenarios.
The paper tackles the problem of learning in strategic classification settings where users modify features to improve outcomes, presenting a practical framework that minimizes strategic empirical risk by differentiating through user responses, with experiments showing its effectiveness across various settings.
Strategic classification regards the problem of learning in settings where users can strategically modify their features to improve outcomes. This setting applies broadly and has received much recent attention. But despite its practical significance, work in this space has so far been predominantly theoretical. In this paper we present a learning framework for strategic classification that is practical. Our approach directly minimizes the "strategic" empirical risk, achieved by differentiating through the strategic response of users. This provides flexibility that allows us to extend beyond the original problem formulation and towards more realistic learning scenarios. A series of experiments demonstrates the effectiveness of our approach on various learning settings.