Ben Adlam
11 papers · 2019–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Academic Marathon (5) π Cross-Pollinator (12)
πΊοΈ
Taxonomy Completionist
(21)
π
Conference Polyglot
(5)
π₯
Mega-Team
(40)
π
Century Club
(11)
β
The Questioner
Conferences
NIPS (6)
ICLR (2)
AISTATS (1)
ICML (1)
JMLR (1)
Top co-authors
Keywords
neural tangent kernel
(3)
double descent
(3)
high-dimensional analysis
(2)
random feature regression
(2)
kernel regression
(2)
kernel methods
(2)
neural network
(2)
domain adaptation
(2)
distribution shift
(2)
convex optimization
(1)
ensemble learning
(1)
stochastic differential equation
(1)
spectral norm
(1)
random matrix theory
(1)
generalization error
(1)
learning dynamics
(1)
random feature
(1)
covariate shift
(1)
generalization guarantee
(1)
implicit regularization
(1)
Papers
Small-scale proxies for large-scale Transformer training instabilities
ICLR 2024
Underspecification Presents Challenges for Credibility in Modern Machine Learning
JMLR 2022
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions
NIPS 2022
A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions
AISTATS 2022
Exploring the Uncertainty Properties of Neural Networksβ Implicit Priors in the Infinite-Width Limit
ICLR 2021
Overparameterization Improves Robustness to Covariate Shift in High Dimensions
NIPS 2021
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
NIPS 2020
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition
NIPS 2020
Finite Versus Infinite Neural Networks: an Empirical Study
NIPS 2020
The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization
ICML 2020
Learning GANs and Ensembles Using Discrepancy
NIPS 2019