Towards ethical machine learning : new algorithms for fairness and privacy / Seth V. Neel.

Format:

Book

Thesis/Dissertation

Author/Creator:

Neel, Seth V., author.

Contributor:

Kearns, Michael J., degree supervisor.

Roth, Aaron L., degree supervisor.

University of Pennsylvania. Department of Statistics, degree granting institution.

Language:

English

Subjects (All):

Artificial intelligence.

Computer science.

Statistics--Penn dissertations.

Penn dissertations--Statistics.

Local Subjects:

Artificial intelligence.

Computer science.

Statistics--Penn dissertations.

Penn dissertations--Statistics.

Genre:

Academic theses.

Physical Description:

1 online resource (236 pages)

Contained In:

Dissertations Abstracts International 82-01B.

Place of Publication:

[Philadelphia, Pennsylvania] : University of Pennsylvania ; Ann Arbor : ProQuest Dissertations & Theses, 2020.

Language Note:

English

System Details:

Mode of access: World Wide Web.

text file

Summary:

The challenge of ensuring that tools for data science and machine learning enforce ethical notions like privacy and fairness is one of the most important facing modern computer scientists. While the last decade has seen a flurry of research in this area, there are still significant challenges to using existing algorithms and definitions in practice. This thesis considers the theoretical questions arising from practical considerations, with an emphasis on machine learning applications. In particular, we make crucial definitions and obtain new results towards answering the following questions: How can we learn optimally private classifiers subject to a hard accuracy constraint? How can we leverage heuristic optimization oracles for private learning while still maintaining rigorous privacy guarantees? How can we extend the coarse fairness protections provided by statistical notions of fairness to richer subgroup classes? How can we learn subject to an individual fairness notion whose metric is not provided, but is instead learned from a panel of experts? Behavioral subject experiments validate theoretical results.

Notes:

Source: Dissertations Abstracts International, Volume: 82-01, Section: B.

Advisors: Kearns, Michael J.; Roth, Aaron L.; Committee members: Weijie Su; Bhaswar Bhattacharya.

Department: Statistics.

Ph.D. University of Pennsylvania 2020.

Local Notes:

School code: 0175

ISBN:

9798662379480

Access Restriction:

Restricted for use by site license.

This item must not be sold to any third party vendors.