Equal Opportunity in Online Classification with Partial Feedback
Abstract
We study an online classification problem with partial feedback in which individuals arrive one at a time from a fixed but unknown distribution, and must be classified as positive or negative. Our algorithm only observes the true label of an individual if they are given a positive classification. This setting captures many classification problems for which fairness is a concern: for example, in criminal recidivism prediction, recidivism is only observed if the inmate is released; in lending applications, loan repayment is only observed if the loan is granted. We require that our algorithms satisfy common statistical fairness constraints (such as equalizing false positive or negative rates --- introduced as "equal opportunity" in Hardt et al. (2016)) at every round, with respect to the underlying distribution. We give upper and lower bounds characterizing the cost of this constraint in terms of the regret rate (and show that it is mild), and give an oracle efficient algorithm that achieves the upper bound.
Additional Information
Supported in part by Israeli Science Foundation (ISF) grant #1044/16, a subcontract on the DARPA Brandeis Project, and the Federmann Cyber Security Center in conjunction with the Israel national cyber directorate. Supported in part by Israeli Science Foundation (ISF) grant #1044/16, a subcontract on the DARPA Brandeis Project, and the Federmann Cyber Security Center in conjunction with the Israel national cyber directorate. Part of this work was done while the author was visiting the Simons Institute for the Theory of Computing. Supported in part by NSF grants AF-1763307, CNS-1253345, a subcontract on the DARPA Brandeis Project, and an Amazon Research award. We thank Nati Srebro for a conversation leading to the question we study here. We thank Michael Kearns for helpful discussions at an early stage of this work.Attached Files
Submitted - 1902.02242.pdf
Files
Name | Size | Download all |
---|---|---|
md5:e282096b751c611f492f87c71275fb58
|
284.2 kB | Preview Download |
Additional details
- Eprint ID
- 96753
- Resolver ID
- CaltechAUTHORS:20190626-152715232
- Israel Science Foundation
- 1044/16
- Defense Advanced Research Projects Agency (DARPA)
- Hebrew University of Jerusalem
- NSF
- AF-1763307
- NSF
- CNS-1253345
- Amazon
- Created
-
2019-06-27Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field