OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
James B Simon
PhD student, University of California Berkeley
Joined
May 2021
Names
James B Simon
(Preferred)
,
James B. Simon
,
James Simon
Emails
****@berkeley.edu
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
Career & Education History
PhD student
University of California Berkeley
(berkeley.edu)
2019
–
Present
Undergrad student
Virginia Tech
(vt.edu)
2014
–
2018
Advisors, Relations & Conflicts
PhD Advisor
Michael R DeWeese
Present
Expertise
deep learning
,
infinite-width models
,
kernel learning
,
Gaussian processes
,
percolation theory
Present
Publications
A "feature ODE" describing the learning behavior of shallow MLPs on simple functions
Joseph Turnbull
,
Berkan Ottlik
,
James B Simon
HiLD at ICML 2026 Poster
Readers:
Everyone
Scientific Methods for Understanding Deep Learning (Sci4DL)
Zahra Kadkhodaie
,
Florentin Guth
,
Sanae Lotfi
,
Davis Brown
,
Antonio Sclocchi
,
Sharvaree Vadgama
,
James B Simon
,
Eero P Simoncelli
ICLR 2026 Workshop Proposals
Readers:
Everyone
Predicting Kernel Regression Learning Curves from Only Raw Data Statistics
Dhruva Karkada
,
Joseph Turnbull
,
Yuxi Liu
,
James B Simon
ICLR 2026 Poster
Readers:
Everyone
FACT: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
Enric Boix-Adserà
,
Neil Rohit Mallinar
,
James B Simon
,
Mikhail Belkin
ICLR 2026 Poster
Readers:
Everyone
Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
Ioannis Bantzis
,
James B Simon
,
Arthur Jacot
ICLR 2026 Poster
Readers:
Everyone
Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
Daniel Kunin
,
Giovanni Luca Marchetti
,
Feng Chen
,
Dhruva Karkada
,
James B Simon
,
Michael R DeWeese
,
Surya Ganguli
,
Nina Miolane
NeurIPS 2025 poster
Readers:
Everyone
Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
Dhruva Karkada
,
James B Simon
,
Yasaman Bahri
,
Michael R DeWeese
NeurIPS 2025 poster
Readers:
Everyone
The Optimization Landscape of SGD Across the Feature Learning Strength
Alexander Atanasov
,
Alexandru Meterez
,
James B Simon
,
Cengiz Pehlevan
ICLR 2025 Poster
Readers:
Everyone
An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
Lijia Zhou
,
James B Simon
,
Gal Vardi
,
Nathan Srebro
ICLR 2024 poster
Readers:
Everyone
More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
James B Simon
,
Dhruva Karkada
,
Nikhil Ghosh
,
Mikhail Belkin
ICLR 2024 poster
Readers:
Everyone
View all 26 publications
Co-Authors
Aarohi Srivastava
Abhinav Rastogi
Abhishek Rao
Abraham J Fetterman
Abraham J. Fetterman
Abu Awal Md Shoeb
Abubakar Abid
Adam Fisch
Adam R. Brown
Adam Santoro
Aditya Gupta
Adrià Garriga-Alonso
Agnieszka Kluska
Aitor Lewkowycz
Akshat Agarwal
Alethea Power
Alex Ray
Alex Warstadt
Alexander Atanasov
Alexander W. Kocurek
Alexandru Meterez
Ali Safaya
Ali Tazarv
Alice Xiang
Alicia Parrish
View all 505 co-authors