My research overlaps with the statistical machine learning, deep learning, and natural language processing communities. I work on developing methods to make machine learning trustworthy and aligned. My current research is centered around privacy, robustness, and alignment aspects of machine learning and AI, with a focus on aspects related to large language models. I am also generally interested in understanding intelligence and how it arises.
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. I also had the fortune to learn from Roger Grosse, Ting-Kam Leonard Wong, Jimmy Ba, and Chris Maddison. I joined the Google AI Residency program afterwards and worked with Geoffrey Hinton, Danny Tarlow, and Mohammad Norouzi.
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