Understanding and Estimating the Adaptability of Domain-Invariant Representations
Name
Chuang-cychuang-SM-EECS-2021-thesis.pdf
Description
Thesis PDF
Size
8 MB
Format
Adobe PDF
Checksum (MD5)
a660b346aa89271861fc48ab1b56bde4
Author(s)
Chuang, Ching-Yao
Advisor(s)
Jegelka, Stefanie
Torralba, Antonio
Date Issued
June 2021
Publisher
Massachusetts Institute of Technology
Abstract
When the test distribution differs from the training distribution, machine learning models can perform poorly and wrongly overestimate their performance. In this work, we aim to better estimate the model’s performance under distribution shift, without supervision. To do so, we use a set of domain-invariant predictors as a proxy for the unknown, true target labels, where the error of this estimation is bounded by the target risk of the proxy model. Therefore, we study the generalization of domain-invariant representations and show that the complexity of the latent representation has a significant influence on the target risk. Empirically, our estimation approach can self-tune to find the optimal model complexity and the resulting models achieve good target generalization, and estimate target error of other models well. Applications of our results include model selection, deciding early stopping, error detection, and predicting the adaptability of a model between domains.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
