Upcoming Dissertation Defenses

April 29, 2025

Thursday, May 1

Student Name: William Marts
Program: PhD Computer Science
Date: Thursday, May 1st
Time: 1:00pm
Place: FEC 2410
Title: "A Systematic Evaluation of Threaded Internode Communication in HPC"
Committee Chair: Dr. Patrick Bridges
Abstract: The codesign of applications and middleware to communicate data between process pairs earlier and in finer segments can improve performance through better utilization of network resources. %Existing work has not evaluated these methodologies using meaningful application impact measures nor empirically evaluated the specifics of their implementation on the co-design of applications and middleware.

In this work I design, develop, test, and utilize new methods of empirically evaluating the performance impacts of threaded fine-grained communication. The combination of the \minimod modular proxy application framework and the Configurable Messaging Benchmark (CMB) enable a detailed exploration of the performance impacts of threaded communication in existing applications, the measurement and evaluation of the thread behavior that impacts communication, and evaluate how the combination of aggregation, user level communication interface, and application communication requirements impacts when and how to best use threaded communication.

Monday, May 5

Student Name: J. Jake Nichol
Program: PhD Computer Science
Date: Monday, May 5th
Time: 9:00am
Place: FEC 3300
Title: " Seeking Etiologies in Complex Systems: From Feature Analysis to Space-Time Causal Discovery with Applications in Climate Science"
Committee Chair: Dr. Melanie Moses
Abstract: Complex systems are difficult to study because of their many interacting parts, emergent phenomena, and feedback loops. These systems underpin all life on Earth. We need improved tools for seeking an understanding of them. I present my investigations into datadriven methods for understanding complex systems, including my invention of a novel causal discovery meta-algorithm for space-time gridded data. I demonstrated machine learning feature importance and causal discovery capabilities for comparing simulated and observed climate data. I developed a new benchmark for modeling space-time dynamics of locally driven phenomena and examined a prominent causal discovery algorithm. Finding that contemporary causal discovery struggles with the high-dimensionality of space-time gridded data, I developed CaStLe, a causal discovery meta-algorithm for recovering the space-time evolution of advective phenomena. Finally, I extended CaStLe to recover multivariate space-time dynamics. This research enhances scientists' capabilities to explore and understand complex systems in our universe.