Preetum Nakkiran

I'm a 4th-year PhD student at Harvard, in the Theory Group and co-organizer of the Harvard ML Theory Group. This semester I'm on sabbatical visiting Jacob Steinhardt at Berkeley.

I'm advised by Madhu Sudan and Boaz Barak, and I recently interned at OpenAI, with Ilya Sutskever.

I'm currently trying to understand why deep learning works.




I am interested in taking a scientific approach to machine learning— to make progress on understanding through basic experiments and foundational theory.

See [publications] for full list of papers.

Machine Learning Theory


Machine Learning

Deep Double Descent
Dynamics of SGD
Gauss's Principle of Least Action

About Me

I did my undergrad in EECS at UC Berkeley. I'm broadly interested in theory and science.

In the past, I have interned at OpenAI (with Ilya Sutskever) and Google Research (with Raziel Alvarez), and have also done research in error-correcting codes, distributed storage, and cryptography.

See also my old website for more. This version borrowed from Luca Trevisan.