Matthieu Wyart
12 papers · 2018–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (3) 🐝 Cross-Pollinator (14)
🏃
Academic Marathon
(7)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(14)
🏆
Keyword Champion
(2)
🔥
Unstoppable
(5)
💎
Century Club
(12)
❓
The Questioner
Conferences
ICML (7)
NIPS (4)
ICLR (1)
Top co-authors
Keywords
generalization error
(4)
convolutional neural network
(2)
lazy training
(2)
feature learning
(2)
neural network
(2)
sparse representation
(1)
self-supervised learning
(1)
deep learning
(1)
neural network optimization
(1)
loss landscape
(1)
eigenvalue decomposition
(1)
kernel regression
(1)
kernel ridge regression
(1)
replica method
(1)
hierarchical structure
(1)
deep neural network
(1)
language model
(1)
random feature
(1)
learning curve
(1)
test error
(1)
Papers
Probing the Latent Hierarchical Structure of Data via Diffusion Models
ICLR 2025
Learning curves theory for hierarchically compositional data with power-law distributed features
ICML 2025
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
ICML 2025
Towards a theory of how the structure of language is acquired by deep neural networks
NIPS 2024
How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
ICML 2024
Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
ICML 2023
What Can Be Learnt With Wide Convolutional Neural Networks?
ICML 2023
Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data
ICML 2022
Learning sparse features can lead to overfitting in neural networks
NIPS 2022
Relative stability toward diffeomorphisms indicates performance in deep nets
NIPS 2021
Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
NIPS 2021
Comparing Dynamics: Deep Neural Networks versus Glassy Systems
ICML 2018