Preetum Nakkiran

I'm a final-year PhD student at Harvard, in the Theory of Computation and ML Theory Groups, advised by Madhu Sudan and Boaz Barak.

I'm currently trying to understand why deep learning works. I do theory by doing experiments.

[publications]     [CV]     [twitter]     preetum@cs.harvard.edu


News:


Research

I take a scientific approach to machine learning— trying to advance understanding through basic experiments and foundational theory. I aim to discover universal principles of learning.

See [publications] for full list of papers.

Machine Learning Theory

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. I am partially supported by a Google PhD Fellowship, and I am grateful for past support from NSF GRFP.

See also my old website for more. This version borrowed in part from Luca Trevisan and Jon Barron.