Understanding and Estimating the Adaptability of Domain-Invariant Representations

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.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2021

Author dc:creator

• Chuang, Ching-Yao

Advisors dc:contributor.advisor

• Jegelka, Stefanie
• Torralba, Antonio

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright MIT

Licence dc:rights.uri

• http://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/139150

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/139150