Interns at Apple (hosted, co-hosted, or collaborated):
- Annabelle Carrell. PhD student, University of Cambridge.
- Lunjia Hu. PhD student, Stanford. (hosted by Parikshit Gopalan)
- Shivam Garg. PhD student, Stanford. (hosted by Kunal Talwar)
- Rylee Thompson. MASc student, University of Guelph. (hosted by Shuangfei Zhai)
- Elan Rosenfeld. PhD student, CMU. (hosted by Fartash Faghri)
Acknowledgements: I have had the pleasure of collaborating with the following excellent students & postdocs (partial list):
News and Olds:
- Sept 2022: 3 out of 6 papers accepted to NeurIPS 2022! The resubmissions will continue until rates improve.
- Aug 2022: I co-organized the Deep Learning Theory Workshop at the Simons Institute in Berkeley, CA.
- May 2022: I've joined Apple ML Research! Job talk [slides]
- Nov 2021: New manuscript on Turing-Universal Learners with Optimal Scaling Laws (free-lunch.org). Also other papers.
- Sept 2021: I have moved to University of California, San Diego.
- July 2021: I defended my thesis! View the [slides], and read the [thesis]. I suggest the Introduction, which is written for general scientific audience.
- 1994: Born
Recent/Upcoming Invited Talks(I'm taking a sabbatical from preparing slides -- please ask one of my excellent co-authors 😀)
- 7 Feb 2022: Stanford talk (Percy Liang group), on Distributional Generalization.
- 15 Dec 2021: Reinforcement Learning Reading Group talk (Marcus Hutter group).
- 7 Dec 2021: Simons Institute talk, on "Is Overfitting Actually Benign?." [slides]
- 2 Dec 2021: Princeton talk (Sanjeev Arora group).
- 30 Nov 2021: CMU ML Faculty Seminar talk.
- 17 Nov 2021: MIT talk (Sasha Rakhlin group), on Distributional Generalization.
- 15 Nov 2021: MIT talk (Poggio Lab), on The Deep Bootstrap Framework.
- Oct 2021: UCSD Theory Seminar talk, on "Theory for Deep Learning, and Deep Learning for Theory." [slides]
- Sept 2021: Deep Learning Classics & Trends talk, on Distributional Generalization. [slides]
- Aug 2021: UToronto talk (Roger Grosse group), on The Deep Bootstrap Framework. [slides]
- June 2021: Deep Learning Classics & Trends talk, on The Deep Bootstrap Framework. [slides]
- Apr 2021: Guest Lecture in ML Theory Course (Boaz Barak), speaking on scaling laws. [slides]
- Apr 2021: UPenn Seminar (Weijie Su group), on Distributional Generalization. [slides]
- Aug 2020: UCLA Big Data and Machine Learning Seminar, on Distributional Generalization.
- Feb 2021: Simons Collaboration Monthly Meeting, speaking on The Deep Bootstrap. [slides]
- Aug 2020: Max Planck+UCLA Math ML Seminar, speaking on Distributional Generalization. [video]
ResearchI take a scientific approach to machine learning— trying to advance understanding through basic experiments and foundational theory.
See [publications] for full list of papers.
Towards an Empirical Theory of Deep Learning
Doctoral dissertation, Harvard University Graduate School of Arts and Sciences. July 2021. [cite]
Machine Learning Theory
The Calibration Generalization Gap
A. Michael Carrell, Neil Mallinar, James Lucas, Preetum Nakkiran
ICML 2022 DFUQ Workshop
Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
Neil Mallinar*, Jamie Simon*, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran
Deconstructing Distributions: A Pointwise Framework of Learning
Gal Kaplun*, Nikhil Ghosh*, Saurabh Garg, Boaz Barak, Preetum Nakkiran
What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
Bogdan Kulynych*, Yao-Yuan Yang*, Yaodong Yu, Jarosław Błasiok, Preetum Nakkiran
Knowledge Distillation: Bad Models Can Be Good Role Models
Gal Kaplun, Eran Malach, Preetum Nakkiran, Shai Shalev-Shwartz
Limitations of the NTK for Understanding Generalization in Deep Learning
Nikhil Vyas, Yamini Bansal, Preetum Nakkiran
Limitations of Neural Collapse for Understanding Generalization in Deep Learning
Like Hui, Mikhail Belkin, Preetum Nakkiran
Turing-Universal Learners with Optimal Scaling Laws
Revisiting Model Stitching to Compare Neural Representations
Yamini Bansal, Preetum Nakkiran, Boaz Barak
The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers
Preetum Nakkiran, Behnam Neyshabur, Hanie Sedghi
Distributional Generalization: A New Kind of Generalization
Preetum Nakkiran*, Yamini Bansal*
- Desk-Rejected from NeurIPS 2020.
- Rejected from ICLR 2021. [reviews]
- Rejected from ICML 2021. [reviews] [rebuttal] [meta]
- Rejected from NeurIPS 2021. [reviews]
- Rejected from ICLR 2022. [reviews]
Learning Rate Annealing Can Provably Help Generalization, Even for Convex Problems
OPT2020 Workshop (Best Student Paper)
Optimal Regularization Can Mitigate Double Descent
Preetum Nakkiran, Prayaag Venkat, Sham Kakade, Tengyu Ma
Deep Double Descent: Where Bigger Models and More Data Hurt
Preetum Nakkiran, Gal Kaplun*, Yamini Bansal*, Tristan Yang, Boaz Barak, Ilya Sutskever
More Data Can Hurt for Linear Regression:
Sample-wise Double Descent
SGD on Neural Networks Learns Functions of Increasing Complexity
Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris, Tristan Yang, Benjamin L. Edelman, Fred Zhang, Boaz Barak
NeurIPS 2019 (Spotlight).
Adversarial Examples are Just Bugs, Too
Adversarial Robustness May Be at Odds With Simplicity
(Merged appears in COLT 2019).
The Generic Holdout:
Preventing False-Discoveries in Adaptive Data Science
Preetum Nakkiran, Jarosław Błasiok
Algorithmic Polarization for Hidden Markov Models
Venkatesan Guruswami, Preetum Nakkiran, Madhu Sudan
General Strong Polarization
Jarosław Błasiok, Venkatesan Guruswami, Preetum Nakkiran, Atri Rudra, Madhu Sudan
Tracking the L2 Norm with Constant Update Time
Chi-Ning Chou, Zhixian Lei, Preetum Nakkiran
Near-Optimal UGC-hardness of Approximating Max k-CSP_R
Pasin Manurangsi, Preetum Nakkiran, Luca Trevisan
Compressing Deep Neural Networks Using a Rank-Constrained Topology
Preetum Nakkiran, Raziel Alvarez, Rohit Prabhavalkar, Carolina Parada
Automatic Gain Control and Multi-style Training for Robust Small-Footprint Keyword Spotting
with Deep Neural Networks
Rohit Prabhavalkar, Raziel Alvarez, Carolina Parada, Preetum Nakkiran, and Tara Sainath
About MeFor 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 grateful for past support from NSF GRFP and the Google PhD Fellowship.
What People are Saying
a "high-level" scientist —colleague (ML)
makes plots and draws lines through them
has merits that outweigh flaws —reviewer 2
a complainer —my partner (among others)
- on science for science's sake
- the "definitional obstacle" to DL theory
- the "Natural Distributions" obstacle to generalization
- resources on causality
- how "causally explaining generalization" is not even wrong
- traps of defining objects which don't exist
- measures of dependence between RVs
- complaints about DL that are not actually about DL
- complaints about "science of ML" missing from ICML
- on calibration and overparameterization