I am currently a postdoctoral researcher at UC Berkeley, where I am fortunate to be hosted by Michael I. Jordan. I have historically worked on a broad set of problems that relate to online optimization, incentive, learning, and their intersection.

Recently, I have been excited about improving efficiency and reliability across the machine learning pipeline (which I think is especially important for generative ai, blog coming soon!) In the first year of my postdoc, I have explored several topics along this line, including diffusion inference, hyperparameter tuning, and data attribution (upcoming).

Prior to joining Berkeley, I was a Master's, and then PhD student in Computer Science at Princeton University. I was extremely fortunate to have my advisor Matt Weinberg as a mentor, and work with many wonderful collaborators. Prior to Princeton, I graduated with University Honors from UIUC with a B.S. in Computer Science and a B.S. in Mathematics.

Fun fact: I did not start off in college as a STEM major.

Here is my CV.