Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published September 7, 2021 | Submitted
Report Open

Who Leads and Who Follows in Strategic Classification?

Abstract

As predictive models are deployed into the real world, they must increasingly contend with strategic behavior. A growing body of work on strategic classification treats this problem as a Stackelberg game: the decision-maker "leads" in the game by deploying a model, and the strategic agents "follow" by playing their best response to the deployed model. Importantly, in this framing, the burden of learning is placed solely on the decision-maker, while the agents' best responses are implicitly treated as instantaneous. In this work, we argue that the order of play in strategic classification is fundamentally determined by the relative frequencies at which the decision-maker and the agents adapt to each other's actions. In particular, by generalizing the standard model to allow both players to learn over time, we show that a decision-maker that makes updates faster than the agents can reverse the order of play, meaning that the agents lead and the decision-maker follows. We observe in standard learning settings that such a role reversal can be desirable for both the decision-maker and the strategic agents. Finally, we show that a decision-maker with the freedom to choose their update frequency can induce learning dynamics that converge to Stackelberg equilibria with either order of play.

Additional Information

We thank Moritz Hardt for an inspiring discussion and helpful feedback on this project. We wish to acknowledge support from the Office of Naval Research under the Vannevar Bush Fellowship program and support from HICON-LEARN (Design of HIgh CONfidence LEARNing-Enabled Systems), Defense Advanced Research Projects Agency award number FA8750-18-C-0101.

Attached Files

Submitted - 2106.12529.pdf

Files

2106.12529.pdf
Files (1.2 MB)
Name Size Download all
md5:e72119f0c6e8a69710c94b2ec352e23e
1.2 MB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 23, 2023