About

I am an Assistant Professor in the Department of Statistics and Actuarial Science at the University of Waterloo, and a Faculty Affiliate at the Vector Institute.

Previously I was a DataX Postdoctoral Research Associate at Princeton University, where I worked with Boris Hanin. I received my PhD from the Department of Statistical Sciences at the University of Toronto, where my advisors were Daniel Roy and Murat Erdogdu.

You can find my CV here.

Research

I am broadly interested in deep learning theory. Most recently, I have been thinking a lot about scaling limits of large neural networks and their training dynamics.

You can find a list of my research work here.

Prospective Students

I am recruiting graduate students with strong foundations in real analysis and probability for theoretical research. Before contacting me, please consult the lecture notes below for a sense of the mathematical background relevant to my current work.

Please follow the application instructions from my department’s graduate admissions page. You can also express interest through Vector’s Graduate Student Program.

Lecture Notes

I am writing a set of Lecture Notes on Neural Network Scaling Limits. Comments and corrections are welcome.

Blog

I attempt to maintain a blog about interesting mathematics that I encounter but that does not necessarily fit into my research program. You can find the current list of my blog posts here.