Preetum Nakkiran

I'm a postdoc with Misha Belkin at UCSD, and part of the NSF/Simons Collaboration on the Theoretical Foundations of Deep Learning.

My research builds conceptual tools for understanding learning systems (including deep learning), using both theory and experiment as appropriate. See the intro of my thesis for more on my motivations and methods.

I recently completed my PhD at Harvard, advised by Madhu Sudan and Boaz Barak. While there, among other things, I co-founded the ML Foundations Group.

[publications]     [CV]     [twitter]     [short-bio]

Online: At this time I am not looking for additional junior collaborators, but this may change in the future (do check back if you're interested). I am always open to specific emails related to or building on my past work. I cannot respond to all email, but will read most. Do bump your email 2x if I fail to respond.
IRL: If you are at UCSD and want to chat in person, about anything, send me a 1-line email :)

Acknowledgements: I have had the pleasure of collaborating with the following excellent students & postdocs (partial list):

News and Olds:

Recent/Upcoming Invited Talks

I'm happy to speak about my works and interests. Currently, I will likely speak about The Deep Bootstrap Framework, Distributional Generalization, or musings about scaling, or science, or theory.


I take a scientific approach to machine learning— trying to advance 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

For talks, you can use this [bio].

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) Google Research (with Raziel Alvarez), Google Brain (with Behnam Neyshabur, Hanie Sedghi), 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.

What People are Saying

a "high-level" scientist   —colleague (ML)

makes plots and draws lines through them
            —colleague (TCS)

has merits that outweigh flaws   —reviewer 2

a complainer   —my girlfriend (among others)

Selected Tweets