Clement Hongler
7 papers · 2018–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🏃 Academic Marathon (6)
🐝
Cross-Pollinator
(4)
🗺️
Taxonomy Completionist
(13)
👑
Triple Crown
📈
Trend Setter
Conferences
ICML (3)
NIPS (3)
ICLR (1)
Top co-authors
Keywords
kernel ridge regression
(2)
kernel methods
(2)
neural tangent kernel
(1)
feature learning
(1)
loss landscape
(1)
gaussian process
(1)
generalization error
(1)
l2 regularization
(1)
random matrix theory
(1)
deep neural network
(1)
implicit regularization
(1)
hidden representation
(1)
affine subspace
(1)
random feature model
(1)
critical point
(1)
overparameterized neural network
(1)
risk prediction
(1)
kernel alignment
(1)
permutation symmetry
(1)
infinite-width limit
(1)
Papers
Arrows of Time for Large Language Models
ICML 2024
Feature Learning in $L_2$-regularized DNNs: Attraction/Repulsion and Sparsity
NIPS 2022
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
ICML 2021
The asymptotic spectrum of the Hessian of DNN throughout training
ICLR 2020
Kernel Alignment Risk Estimator: Risk Prediction from Training Data
NIPS 2020
Implicit Regularization of Random Feature Models
ICML 2020
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
NIPS 2018