My research interests are statistical machine learning, deep learning, and natural language processing. I work on developing techniques to make machine learning systems trustworthy. My current research is centered around privacy, robustness, fairness, and alignment aspects of machine learning and AI, with a focus on problems related to large language models.
Before, I worked on a variety of topics spanning Bayesian statistics, neural networks, numerical methods, and applied probability. I did my undergrad at the University of Toronto, where I did research with David Duvenaud and Murat Erdogdu, and collaborated with Roger Grosse, Ting-Kam Leonard Wong, and Jimmy Ba. I joined the Google AI Residency program afterwards and worked with Geoffrey Hinton, Danny Tarlow, and Mohammad Norouzi, and collaborated with Chris Maddison.
I’m grateful for the support of a Stanford Graduate Fellowship.
PhD in CS, 2021 -
BSc in CS, Math & Stats, 2015 - 2019
University of Toronto