Beyond Statistical Fairness / Christopher Sangyeon Jung.

Format:

Book

Thesis/Dissertation

Author/Creator:

Jung, Christopher Sangyeon, author.

Contributor:

University of Pennsylvania. Computer and Information Science, degree granting institution.

Language:

English

Subjects (All):

Computer science.

Computer and Information Science--Penn dissertations.

Penn dissertations--Computer and Information Science.

Local Subjects:

Computer science.

Computer and Information Science--Penn dissertations.

Penn dissertations--Computer and Information Science.

Physical Description:

1 online resource (306 pages)

Distribution:

Ann Arbor : ProQuest Dissertations & Theses, 2022

Contained In:

Dissertations Abstracts International 84-01B.

Place of Publication:

[Philadelphia, Pennsylvania] : University of Pennsylvania, 2022.

Language Note:

English

Summary:

In recent years, a great deal of fairness notions has been proposed. Yet, most of them take a reductionist approach by indirectly viewing fairness as equalizing some error statistic across pre-defined groups. This thesis aims to explore some ideas as to how to go beyond such statistical fairness frameworks.First, we consider settings in which the right notion of fairness may not be captured by simple mathematical definitions but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. By asking stakeholders to make pairwise comparisons to learn which pair of individuals should be treated similarly, we show how to approximately learn the most accurate classifier or converge to such one subject to the elicited fairness constraints. We consider an offline setting where the pairwise comparisons must be made prior to training a model and an online setting where one can continually provide fairness feedback to the deployed model in each round. We also report preliminary findings of a behavioral study of our framework using human-subject fairness constraints elicited on the COMPAS criminal recidivism dataset.Second, unlike most of the statistical fairness framework that promises fairness for pre-defined and often coarse groups, we provide fairness guarantees for finer subgroups, such as all possible intersections of the pre-defined groups, in the context of uncertainty estimation in both offline and online setting. Our framework gives uncertainty guarantees that are more locally sensible than the ones given by conformal prediction techniques; our uncertainty estimates are valid even when averaged over any subgroup, but uncertainty estimates in conformal predictions are usually only valid when averaged over the entire population.

Notes:

Source: Dissertations Abstracts International, Volume: 84-01, Section: B.

Advisors: Roth, Aaron; Kearns, Michael; Committee members: Doriban, Edgar; Kannan, Sampath; Vohra, Rakesh; Wu, Steven.

Department: Computer and Information Science.

Ph.D. University of Pennsylvania 2022.

Local Notes:

School code: 0175

ISBN:

9798834092520

Access Restriction:

Restricted for use by site license.