Sequential Strategic Screening

Lee Cohen, Saeed Sharifi -Malvajerdi, Kevin Stangl, Ali Vakilian, Juba Ziani
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6279-6295, 2023.

Abstract

We initiate the study of strategic behavior in screening processes with multiple classifiers. We focus on two contrasting settings: a "conjunctive” setting in which an individual must satisfy all classifiers simultaneously, and a sequential setting in which an individual to succeed must satisfy classifiers one at a time. In other words, we introduce the combination of strategic classificationwith screening processes. We show that sequential screening pipelines exhibit new and surprising behavior where individuals can exploit the sequential ordering of the tests to "zig-zag” between classifiers without having to simultaneously satisfy all of them. We demonstrate an individual can obtain a positive outcome using a limited manipulation budget even when far from the intersection of the positive regions of every classifier. Finally, we consider a learner whose goal is to design a sequential screening process that is robust to such manipulations, and provide a construction for the learner that optimizes a natural objective.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-cohen23a, title = {Sequential Strategic Screening}, author = {Cohen, Lee and Sharifi -Malvajerdi, Saeed and Stangl, Kevin and Vakilian, Ali and Ziani, Juba}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {6279--6295}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/cohen23a/cohen23a.pdf}, url = {https://proceedings.mlr.press/v202/cohen23a.html}, abstract = {We initiate the study of strategic behavior in screening processes with multiple classifiers. We focus on two contrasting settings: a "conjunctive” setting in which an individual must satisfy all classifiers simultaneously, and a sequential setting in which an individual to succeed must satisfy classifiers one at a time. In other words, we introduce the combination of strategic classificationwith screening processes. We show that sequential screening pipelines exhibit new and surprising behavior where individuals can exploit the sequential ordering of the tests to "zig-zag” between classifiers without having to simultaneously satisfy all of them. We demonstrate an individual can obtain a positive outcome using a limited manipulation budget even when far from the intersection of the positive regions of every classifier. Finally, we consider a learner whose goal is to design a sequential screening process that is robust to such manipulations, and provide a construction for the learner that optimizes a natural objective.} }
Endnote
%0 Conference Paper %T Sequential Strategic Screening %A Lee Cohen %A Saeed Sharifi -Malvajerdi %A Kevin Stangl %A Ali Vakilian %A Juba Ziani %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-cohen23a %I PMLR %P 6279--6295 %U https://proceedings.mlr.press/v202/cohen23a.html %V 202 %X We initiate the study of strategic behavior in screening processes with multiple classifiers. We focus on two contrasting settings: a "conjunctive” setting in which an individual must satisfy all classifiers simultaneously, and a sequential setting in which an individual to succeed must satisfy classifiers one at a time. In other words, we introduce the combination of strategic classificationwith screening processes. We show that sequential screening pipelines exhibit new and surprising behavior where individuals can exploit the sequential ordering of the tests to "zig-zag” between classifiers without having to simultaneously satisfy all of them. We demonstrate an individual can obtain a positive outcome using a limited manipulation budget even when far from the intersection of the positive regions of every classifier. Finally, we consider a learner whose goal is to design a sequential screening process that is robust to such manipulations, and provide a construction for the learner that optimizes a natural objective.
APA
Cohen, L., Sharifi -Malvajerdi, S., Stangl, K., Vakilian, A. & Ziani, J.. (2023). Sequential Strategic Screening. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:6279-6295 Available from https://proceedings.mlr.press/v202/cohen23a.html.

Related Material