Strategic Classification Made Practical

Sagi Levanon, Nir Rosenfeld
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6243-6253, 2021.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-levanon21a, title = {Strategic Classification Made Practical}, author = {Levanon, Sagi and Rosenfeld, Nir}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {6243--6253}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/levanon21a/levanon21a.pdf}, url = {https://proceedings.mlr.press/v139/levanon21a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Strategic Classification Made Practical %A Sagi Levanon %A Nir Rosenfeld %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-levanon21a %I PMLR %P 6243--6253 %U https://proceedings.mlr.press/v139/levanon21a.html %V 139 %X 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.
APA
Levanon, S. & Rosenfeld, N.. (2021). Strategic Classification Made Practical. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:6243-6253 Available from https://proceedings.mlr.press/v139/levanon21a.html.

Related Material