Distributionally Robust Machine Intelligence for Medicine and Scientific Discovery Michael S Yao

Format:

Book

Thesis/Dissertation

Author/Creator:

Yao, Michael S., author.

Contributor:

University of Pennsylvania. Bioengineering., degree granting institution.

Language:

English

Subjects (All):

0202.

0564.

0984.

Local Subjects:

0202.

0564.

0984.

Physical Description:

1 electronic resource (263 pages)

Contained In:

Dissertations Abstracts International 87-07B

Place of Publication:

Ann Arbor : ProQuest Dissertations and Theses, 2025

Language Note:

English

Summary:

Machine learning systems are becoming increasingly adopted in high-stakes applications from clinical medicine to scientific discovery. In these settings, the predictions made by learned algorithms can have profound consequences. While modern machine learning models have achieved impressive empirical performance, they often behave unpredictably outside their training distribution, raising concerns about their reliability, fairness, and safety. These limitations are especially pronounced in domains where failure can be costly or irreversible, such as healthcare and scientific discovery. As a result, there is a growing need for AI systems that are not only performant, but also safe and generalizable when faced with new, diverse, and unforeseen inputs in the wild. This dissertation investigates how we can design such ML systems to make reliable predictions across the range of inputs they might encounter in the real world. We explore this question through two complementary hypotheses. First, by incorporating structured priors generated from natural language and domain knowledge of biomedical systems directly into model architectures, we can build systems that are more generalizable. We show how such ML systems that are interpretable-by-design are better aligned with human reasoning to solve challenging domain-specific tasks. Second, we show how leveraging adversarial supervision from auxiliary neural networks can help us estimate when and where black-box model predictions can be trusted. We demonstrate how this framework can be readily adapted to solve a wide range of optimization problems in medicine and science. In summary, this dissertation provides a principled framework for making machine learning systems more aligned, robust, and actionable in safety-critical biomedical applications

Notes:

Advisors: Gee, James C.; Bastani, Osbert Committee members: Johnson, Kevin B.; Tisdall, M. Dylan; Yatskar, Mark; Witschey, Walter R.

Source: Dissertations Abstracts International, Volume: 87-07, Section: B.

Ph.D. University of Pennsylvania 2025

Vendor supplied data

Local Notes:

School code: 0175

ISBN:

9798276007113

Access Restriction:

Restricted for use by site license