Methods for Enhancing Robustness and Generalization in Machine Learning
Name
schechter-amitsch-sm-eecs-2024-thesis.pdf
Description
Thesis PDF
Size
4.22 MB
Format
Adobe PDF
Checksum (MD5)
b6758f1ac05ff1c29151c5325648cd0c
Author(s)
Schechter, Amit
Advisor(s)
Jaakkola, Tommi S.
Date Issued
September 2024
Publisher
Massachusetts Institute of Technology
Abstract
We propose two methods for improving subgroup robustness and out of distribution generalization of machine learning models. First we introduce a formulation of Group DRO with soft group assignment. This formulation can be applied to data with noisy or uncertain group labels, or when only a small subset of the training data has group labels. We propose a modified loss function, explain how to apply it to data with noisy group labels as well as data with missing or few group labels, and perform experiments to demonstrate its effectiveness. In the second part, we propose an invariant decision tree objective that aims to improve the robustness of tree-based models and address a common failure mode of existing methods for out-of-domain generalization. We demonstrate the benefits of this method both theoretically and empirically. Both these approaches are designed to enhance machine learning models’ performance under distribution shift.
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
