8 papers
Welfare-Optimal Classification with Accuracy Auctions
Bana Sadi, Eden Saig, Nir Rosenfeld
Prediction algorithms are increasingly used to inform decisions about humans, but maximizing accuracy-the standard learning objective-is not necessarily optimal for this purpose. I…
Strategic PAC Learnability via Geometric Definability
Yuval Filmus, Shay Moran, Elizaveta Nesterova +2
Strategic classification studies learning settings in which individuals can modify their features, at a cost, in order to influence the classifier's decision. A central question is…
Ambiguous Strategic Classification
Ivri Hikri, Nir Rosenfeld
A common assumption in strategic classification is that the classifier is public knowledge. However, it remains unclear whether, and why, a system would choose to commit to full di…
The Role of Causal Features in Strategic Classification for Robustness and Alignment
Antonio Gois, Sophia Gunluk, Nir Rosenfeld +3
In strategic classification, an institution (e.g., a bank) anticipates adaptation from users who change their features to increase utility in a classification task (e.g., loan repa…
Strategic Classification with Non-Linear Classifiers
Benyamin Trachtenberg, Nir Rosenfeld
In strategic classification, the standard supervised learning setting is extended to support the notion of strategic user behavior in the form of costly feature manipulations made…
Learning Classifiers That Induce Markets
Yonatan Sommer, Ivri Hikri, Lotan Amit +1
When learning is used to inform decisions about humans, such as for loans, hiring, or admissions, this can incentivize users to strategically modify their features, at a cost, to o…