PhD Thesis Defense

This dissertation explores the development and application of clinical foundation models (FMs).

Probabilistic models are essential for understanding complex systems across various fields, but inference in these models is often intractable.

This thesis addresses reconstruction tasks for static and dynamic structures, focusing on buildings and human faces exploring representations...

This thesis focuses on the development and application of adaptive machine-learning models.

In this work we produce verified code for a Seldonian algorithm validation test.

This thesis addresses these challenges through a series of innovations in multi-task learning.

This research advances methodologies for analyzing textual content from large-scale online datasets, interpreting message intent, retrieving  knowledge...

This thesis proposes an alternative path toward intelligent control by  drawing inspiration from biological systems and exploring the concept of time-aware...

This proposal addresses three problems in fair ML.

Our algorithms, Greedy Expert Round Robin and FairSequence, assign experts in such a way that no request "envies" another request's assigned experts.

In this PhD Thesis Defense, Chen will explore neural network architectures that facilitate joint learning across varied tasks.

In this proposal, Lee will present optimal online algorithms for energy optimization in the competitive analysis setting.