Ben Adlam
11 papers · 2019–2024 · 5 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 ↓+4 more ↓ Show less ↑
🗺️ Taxonomy Completionist (23) 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze
👥
Mega-Team · Squad
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(52)
Top co-authors
Research topics
Machine Learning
(11)
Optimization & Theory · Machine Learning
(10)
Deep Learning
(9)
Optimization & Theory · Deep Learning
(6)
Application Areas
(3)
Models
(3)
Artificial Intelligence
(2)
Mathematics & Optimization
(2)
Architectures
(2)
Bayesian & Probabilistic
(1)
Core AI
(1)
Core Methods
(1)
Learning Types
(1)
Mathematics
(1)
Optimization
(1)
Keywords
neural tangent kernel
(3)
double descent
(3)
high-dimensional analysis
(2)
distribution shift
(2)
random feature regression
(2)
kernel regression
(2)
domain adaptation
(2)
neural network
(2)
kernel methods
(2)
neural network gaussian process
(2)
convex optimization
(1)
generalization error
(1)
covariate shift
(1)
ensemble learning
(1)
theoretical analysis
(1)
implicit regularization
(1)
neural network optimization
(1)
learning rate
(1)
random matrix theory
(1)
model calibration
(1)
Papers
Small-scale proxies for large-scale Transformer training instabilities
ICLR 2024
A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions
AISTATS 2022
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions
NeurIPS 2022
Underspecification Presents Challenges for Credibility in Modern Machine Learning
JMLR 2022
Exploring the Uncertainty Properties of Neural Networks’ Implicit Priors in the Infinite-Width Limit
ICLR 2021
Overparameterization Improves Robustness to Covariate Shift in High Dimensions
NeurIPS 2021
Finite Versus Infinite Neural Networks: an Empirical Study
NeurIPS 2020
The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization
ICML 2020
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
NeurIPS 2020
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition
NeurIPS 2020
Learning GANs and Ensembles Using Discrepancy
NeurIPS 2019