James B Simon
5 papers · 2022–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Keywords
stochastic gradient descent
(2)
representation learning
(2)
feature learning
(1)
embedding learning
(1)
self-supervised learning
(1)
neural network optimization
(1)
reproducing kernel hilbert space
(1)
kernel ridge regression
(1)
optimization landscape
(1)
test error
(1)
barlow twin
(1)
saddle point
(1)
mini-batch sampling
(1)
random feature regression
(1)
gaussian universality
(1)
neural network width
(1)
lazy training
(1)
ridge penalty
(1)
local maxima
(1)
test risk
(1)
Papers
The Optimization Landscape of SGD Across the Feature Learning Strength
ICLR 2025
An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
ICLR 2024
More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
ICLR 2024
On the Stepwise Nature of Self-Supervised Learning
ICML 2023
SGD Can Converge to Local Maxima
ICLR 2022