PhD Thesis Defense
PhD Thesis Defense: Sohaib Ahmad, Optimized Resource Allocation for Serving Deep Learning Models
This thesis aims to maximize the resource efficiency of DL model serving by
optimizing resource allocation.
PhD Thesis Defense: Erica Cai, From Text to Networks: Enabling and Investigating Social Measurement via Low-Resource Knowledge Graph Extraction
The thesis is motivated by the challenge of extracting structured instances of action or relationship occurrences from large amounts of unstructured text to...
PhD Thesis Defense: Bin Wang, Resource Allocation for Latency-Sensitive Applications in Edge Environments
In this thesis, Wang addresses this gap by presenting model-driven resource allocation algorithms for latency-sensitive applications...
PhD Thesis Defense: Dmitry Petrov, Structure-Aware Shape and Image Synthesis
This thesis proposes an alternative path toward intelligent control by drawing inspiration from biological systems and exploring the concept of time-aware...
Advancing Precision Health with Clinical Foundation Models
This dissertation explores the development and application of clinical foundation models (FMs).
PhD Thesis Defense: Abhinav Agrawal, Towards Reliable Black-Box Variational Inference
Probabilistic models are essential for understanding complex systems across various fields, but inference in these models is often intractable.
PhD Thesis Defense: Pratheba Selvaraju, Exploring Representations for 3D Reconstruction From Impaired Real-World
This thesis addresses reconstruction tasks for static and dynamic structures, focusing on buildings and human faces exploring representations...
PhD Thesis Defense: Iman Deznabi, Adaptive Deep Learning Models for Personalized Modeling of Heterogeneous Time-series Data
This thesis focuses on the development and application of adaptive machine-learning models.
PhD Thesis Defense: Jared Yeager, Machine Checked Verification of Validation Tests for Seldonian Algorithms Machine Checked Verification of Validation Tests for Seldonian Algorithms
In this work we produce verified code for a Seldonian algorithm validation test.
PhD Thesis Defense: Lijun Zhang, Advanced Resource-Efficient Multi-Task Learning
This thesis addresses these challenges through a series of innovations in multi-task learning.
PhD Thesis Defense: Devdhar Patel, Time Aware Intelligence for Efficient and Resilient Control
This thesis proposes an alternative path toward intelligent control by drawing inspiration from biological systems and exploring the concept of time-aware...
Data Driven Expert Assignment
Our algorithms, Greedy Expert Round Robin and FairSequence, assign experts in such a way that no request "envies" another request's assigned experts.