Math & ML for Safer Technology and Better Medicine

Thanks for your interest in my work! I am a Ph.D. student in the Department of Mechanical and Aersopace Engineering at UC San Diego.

I do research in control theory, a branch of applied math that is used across engineering disciplines. Control theory intersects with machine learning to form reinforcement learning, the third of the core ML paradigms. I work on (1) making algorithms for control and reinforcement learning safer in general and (2) specifically applying these algorithms in biology and medicine.

I am grateful to be advised by Dr. Sylvia Herbert and Dr. Boris Kramer. I am also grateful to the various programs that have supported my work: the NIH Intramural Research Training Award, the NSF Graduate Research Fellowship Program, the NIH-UCSD Interfaces Training Grant, and the ARCS Foundation Scholarship.

Prior education and training

I completed my undergraduate degree in biomedical engineering at Johns Hopkins University, with a focus in computational biology and a minor in computational medicine. Afterwards, I did research in computational biology at the National Institutes of Health for two years, and I subsequently obtained my master’s degree in biological engineering from MIT. While at MIT, I did research at the intersection of biology and control theory, leading to my decision to do a Ph.D. in the latter.

Why control theory?

We live in a world increasingly reliant on “black-box” control algorithms. They are already being used in self-driving cars and robotics, and they will progressively become more central to bioscience and clinical decision-making. While these technologies can be highly performant, they often fail in unpredictable and perplexing ways (similar to how chat-bots hallucinate).

I want to help make our algorithms safer. Doing so involves a lot of math and computer science, but also a lot of domain knowledge, so I have to (really get to) speak many languages to do my work. I also love my research because on a day-to-day level, it involves solving interesting puzzles and close collaboration with many amazing colleagues.