Ludovic Stephan

Chemistry · Physical Sciences

11h-index283citations38works3.42yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Analytical chemistry methods development(7), Neural Networks and Applications(6), Complex Network Analysis Techniques(5), Stochastic Gradient Optimization Techniques(4), Sparse and Compressive Sensing Techniques(3)

Publications38 total

Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
arXiv (Cornell University)·2025Open Access
Computational complexity of deep learning: fundamental limitations and empirical phenomena
Journal of Statistical Mechanics Theory and Experiment·2024· 1 citedOpen Access
Universality laws for Gaussian mixtures in generalized linear models*
Journal of Statistical Mechanics Theory and Experiment·2024· 5 citedOpen Access
Semiparametric Estimation of Individual Coefficients in a Dyadic Link Formation Model Lacking Observable Characteristics
arXiv (Cornell University)·2024Open Access
Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs
arXiv (Cornell University)·2024· 1 citedOpen Access
Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions
arXiv (Cornell University)·2024Open Access
Gaussian universality of perceptrons with random labels
Physical review. E·2024· 17 citedOpen Access
Phase diagram of stochastic gradient descent in high-dimensional two-layer neural networks <sup>*</sup>
Journal of Statistical Mechanics Theory and Experiment·2023· 6 citedOpen Access
A Trimming Estimator for the Latent-Diffusion-Observed-Adoption Model
arXiv (Cornell University)·2023Open Access
Moment-Based Estimation of Diffusion and Adoption Parameters in Networks
arXiv (Cornell University)·2023Open Access
How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
arXiv (Cornell University)·2023· 7 citedOpen Access
Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
arXiv (Cornell University)·2023· 1 citedOpen Access
A non-backtracking method for long matrix and tensor completion
arXiv (Cornell University)·2023· 1 citedOpen Access
Universality laws for Gaussian mixtures in generalized linear models
arXiv (Cornell University)·2023Open Access
Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation
arXiv (Cornell University)·2023· 4 citedOpen Access
From high-dimensional &amp; mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks
arXiv (Cornell University)·2023· 3 citedOpen Access
Sparse random hypergraphs: Non-backtracking spectra and community detection
2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS)·2022· 7 citedOpen Access
Sparse random hypergraphs: Non-backtracking spectra and community detection
arXiv (Cornell University)·2022Open Access
Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks
arXiv (Cornell University)·2022· 10 citedOpen Access
Non-backtracking spectra of weighted inhomogeneous random graphs
arXiv (Cornell University)·2020· 3 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Florent Krząkała(12), Philippe Giamarchi(11), Bruno Loureiro(11), Lenka Zdeborová(6), Laure Burel-Deschamps(5), Luca Arnaboldi(5), A. Le Bihan(4), Y. Lijour(4), Luca Pesce(4), Alicia Maroto(3), R. Olier(3), Laure Deschamps(3), Jean-Yves Cabon(3), O. Brede(3), László Wojnárovits(3), T. Taplick(3), Yatin Dandi(3), Yizhe Zhu(3), Olivier Maurice Aly Mbaye(2), Mame Diabou Gaye‐Seye(2)