I am a current M.S. student in Mathematics at Clemson University, conducting research under Dr. Chris McMahan and Dr. Rafael D'Oliveira at the intersection of differential privacy and statistics. I also work on large-scale statistical modeling under Dr. Hudson Smith.
I received my B.S. in Computer Science with Honors from Clemson, where I conducted undergraduate research in side-channel attacks and hardware cybersecurity under Dr. Zhenkai Zhang.
I'm broadly interested in information theory, differential privacy, cryptography, and data science, and am most excited by opportunities to apply them in highly interdisciplinary contexts.
Sample pooling is simultaneously cost-effective, statistically efficient, and private! We explore the privacy-utility tradeoffs of sample pooling and uncover surprising results about its privacy guarantees and estimation efficiency. We introduce a theoretical framework for designing optimal experiments, which has many practical applications in real-world disease surveillance.
Hawkes processes are flexible, interpretable, and can capture sophisticated interactions, but severely suffer from scaling. We look at novel theoretical and practical optimizations that enable fitting a multivariate Hawkes process model on massive and rich social media data. We also provide a feature-rich, open-source, optimized Hawkes process library.