Ludovic Stephan
10 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15) 🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge
🌍
Conference Polyglot
(4)
🗺️
Taxonomy Completionist
(15)
📈
Trend Setter
💎
Century Club
(10)
❓
The Questioner
Conferences
COLT (5)
ICML (2)
NIPS (2)
JMLR (1)
Top co-authors
Research topics
Keywords
stochastic gradient descent
(2)
neural network
(2)
spectral method
(2)
high-dimensional analysis
(2)
generalized linear model
(2)
low-rank approximation
(1)
empirical risk minimization
(1)
feature learning
(1)
eigenvector perturbation
(1)
graph inference
(1)
singular value decomposition
(1)
high-dimensional statistics
(1)
matrix completion
(1)
neural network dynamics
(1)
random graph
(1)
generalization error
(1)
tensor completion
(1)
phase transition
(1)
stochastic block model
(1)
gradient descent
(1)
Papers
Community detection with the Bethe-Hessian
COLT 2025
How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
JMLR 2024
A non-backtracking method for long matrix and tensor completion
COLT 2024
Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
ICML 2024
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks
COLT 2023
Universality laws for Gaussian mixtures in generalized linear models
NIPS 2023
Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
ICML 2023
Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks
NIPS 2022
Planting trees in graphs, and finding them back
COLT 2019
Robustness of Spectral Methods for Community Detection
COLT 2019