Fair, Robust, and Calibrated Deep Learning with Heavy-Tailed Subgroups
Name
hampton-lelia-sm-eecs-2023-thesis.pdf
Description
Thesis PDF
Size
1.04 MB
Format
Adobe PDF
Checksum (MD5)
56a3e1904473ca04cd15576bcc8870ff
Author(s)
Hampton, Lelia Marie
Advisor(s)
Pentland, Alexander P.
Date Issued
June 2023
Publisher
Massachusetts Institute of Technology
Abstract
To deploy safe machine learning systems in the real world, we must ensure they are fair, robust, and calibrated. However, heavy-tails pose a challenge to this mandate, especially since real world data is often imbalanced and marginalized subgroups tend to be underrepresented. To move toward safer systems, we present two studies on fair pre-processing and ensemble learning, respectively. We show that fair pre-processing comes with a fairness-robustness-calibration tradeoff, and we present a novel adaptive sampling algorithm to overcome this tradeoff. Furthermore, we demonstrate that ensemble learning on its own increases the fairness, robustness, and calibration of machine learning models. The adaptive sampling algorithm and ensemble learning present opportunities for practitioners to overcome this tradeoff in practice.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
