publications

2023

  1. From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks
    Luca Arnaboldi, Ludovic Stephan, Florent Krzakala and Bruno Loureiro
    Feb 2023
    arXiv
  2. Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation
    Luca Pesce, Florent Krzakala, Bruno Loureiro and Ludovic Stephan
    Feb 2023
    arXiv
  3. Universality laws for Gaussian mixtures in generalized linear models
    Yatin Dandi, Ludovic Stephan, Florent Krzakala, Bruno Loureiro and Lenka Zdeborová
    Feb 2023
    arXiv

2022

  1. Non-backtracking spectra of weighted inhomogeneous random graphs
    Ludovic Stephan and Laurent Massoulié
    Mathematical Statistics and Learning, Dec 2022
    arXiv
  2. Sparse random hypergraphs: Non-backtracking spectra and community detection
    Ludovic Stephan and Yizhe Zhu
    In 2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS), Oct 2022
    arXiv
  3. Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension
    Federica Gerace, Florent Krzakala, Bruno Loureiro, Ludovic Stephan and Lenka Zdeborová
    May 2022
    arXiv
  4. NeurIPS
    Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks
    Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro, Florent Krzakala and Lenka Zdeborová
    May 2022
    arXiv

2021

  1. A simpler spectral approach for clustering in directed networks
    Simon Coste and Ludovic Stephan
    Feb 2021
    arXiv

2019

  1. COLT
    Planting trees in graphs, and finding them back
    Laurent Massoulié, Ludovic Stephan and Don Towsley
    In Conference on Learning Theory, Jun 2019
    arXiv
  2. COLT
    Robustness of Spectral Methods for Community Detection
    Ludovic Stephan and Laurent Massoulié
    In Conference on Learning Theory, Jun 2019
    arXiv