Learning the Distribution Shift in Performative Prediction
Abstract Number:
3543
Submission Type:
Contributed Abstract
Contributed Abstract Type:
Paper
Participants:
Daniele Bracale (1), Subha Maity (1), Moulinath Banerjee (1), Yuekai Sun (2)
Institutions:
(1) University of Michigan, N/A, (2) N/A, N/A
Co-Author(s):
First Author:
Presenting Author:
Abstract Text:
In many prediction problems, the predictive model affects the sampling distribution. For example, job applicants may doctor their resumes to get them past resume screening systems. Such distribution shifts are especially common in social computing, but methods for learning such distribution shifts from data are scarce. Drawing inspiration from a microeconomic model that characterizes agents in labor markets, we introduce a novel approach for learning the distribution shift. This approach assumes that the agents in the population are rational and adapt to the predictive model by choosing from a finite set of actions. We demonstrate, both empirically and theoretically, that learning the distribution shift and plugging it into an existing method for performative prediction, which necessitates knowledge of the distribution map, is (statistically) more efficient than zeroth-order methods that avoid learning the distribution map.
Keywords:
Strategic classification|Performative prediction|Distribution shift|Cost estimation| |
Sponsors:
Section on Nonparametric Statistics
Tracks:
Applications of nonparametric methods
Can this be considered for alternate subtype?
Yes
Are you interested in volunteering to serve as a session chair?
No
I have read and understand that JSM participants must abide by the Participant Guidelines.
Yes
I understand that JSM participants must register and pay the appropriate registration fee by June 1, 2024. The registration fee is non-refundable.
I understand
You have unsaved changes.