Timezone: »

 
Spotlight
Strategic Classification Made Practical
Sagi Levanon · Nir Rosenfeld

Tue Jul 20 05:35 AM -- 05:40 AM (PDT) @
in Deep Learning Applications »

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, which we achieve 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.

Keywords: Social Aspects of Machine Learning

Author Information

Sagi Levanon (Technion)
Nir Rosenfeld (Harvard)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors