Picture for Ludovic Stephan

Ludovic Stephan

Community detection with the Bethe-Hessian

Add code
Nov 05, 2024
Figure 1 for Community detection with the Bethe-Hessian
Viaarxiv icon

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs

Add code
Jun 04, 2024
Viaarxiv icon

Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions

Add code
May 24, 2024
Viaarxiv icon

Learning Two-Layer Neural Networks, One Step at a Time

Add code
May 29, 2023
Viaarxiv icon

Escaping mediocrity: how two-layer networks learn hard single-index models with SGD

Add code
May 29, 2023
Viaarxiv icon

Universality laws for Gaussian mixtures in generalized linear models

Add code
Feb 17, 2023
Viaarxiv icon

Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation

Add code
Feb 17, 2023
Viaarxiv icon

From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks

Add code
Feb 12, 2023
Viaarxiv icon

Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension

Add code
May 26, 2022
Figure 1 for Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension
Figure 2 for Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension
Figure 3 for Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension
Figure 4 for Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension
Viaarxiv icon

Sparse random hypergraphs: Non-backtracking spectra and community detection

Add code
Mar 14, 2022
Figure 1 for Sparse random hypergraphs: Non-backtracking spectra and community detection
Figure 2 for Sparse random hypergraphs: Non-backtracking spectra and community detection
Figure 3 for Sparse random hypergraphs: Non-backtracking spectra and community detection
Figure 4 for Sparse random hypergraphs: Non-backtracking spectra and community detection
Viaarxiv icon