Romain Couillet | Spectral clustering in sparse and heterogeneous networks

Показать описание

Watch Romain Couillet's talk, presented by Lorenzo Dall’Amico, during the First French-German Meeting in Physics, Mathematics and Artificial Intelligence Theory that took place from November 4 to 6, 2019 in Paris.
Abstract:
Spectral clustering is one of the most popular, yet still incompletely understood, methods for community detection on graphs. This talk presents a spectral clustering algorithm based on the Bethe-Hessian matrix for sparse and heterogeneous graphs. The proposed algorithm is capable of retrieving communities in this setting and to accurately estimate the number of communities. Strong connections are presented with other commonly used spectral clustering techniques, from both statistical physics and mathematics perspectives.
_____
Follow us on:

Рекомендации по теме

Romain Couillet | Spectral clustering in sparse and heterogeneous networks

Romain Couillet | Spectral clustering in sparse and heterogeneous networks

Random Matrix Advances in Machine Learning - Couillet - Workshop 3 - CEB T1 2019

Romain Couillet -- Mini course: Why Random Matrices can Change the Future of Research in AI?

Théorie des matrices aléatoires et intelligence artificielle par Romain Couillet

Spectral Clustering Oracles in Sublinear Time

Spectral methods for graph clustering

TOPML Workshop 2021: Lightning Talk Session #1

AMATH Seminar: Random walks on graphs and hypergraphs: eigenvalues and clustering

2- Matrices aléatoires et apprentissage automatique en grandes dimensions

[Conférence] JP. ROUCHAUD, M. MEZARD, S. MALLAT, L. ZDEBOROVA, R. COUILLET - Discussion autour de l

Optimization meets machine learning for neuroimaging - Gramfort - Workshop 3 - CEB T1 2019

Fred Hamprecht | Signed graph partitioning: an important computer vision primitive

Z. Liao: Recent Advances in Random Matrix Theory for Modern Machine Learning

Teasing poster: Mathematics, Signal Processing and Learning

Random Matrix Theory for High-Dimensional Time Series

Sublinear Time and Space Algorithms for Correlation Clustering via Sparse-Dense Decompositions

GRETSI 2022 - Table Ronde - Transition Energétique

Zhenyu Liao -- A Random Matrix Viewpoint of Learning with Gradient Descent

Recent free probability methods for large random matrices: computational aspects for non s... Part I

Lu Wei: Insights into Large Complex Systems via Random Matrix Theory

DOE CSGF 2018: Distributed Sparse Inverse Covariance Estimation from fMRI Data for Segmenting the...

Random Matrix Theory approach to Deep Learning Optimisation and Generalisation [in English]

Mohamed El Amine Seddik - Random Matrix Theory for Big-Data and Machine Learning

Vehle bethe hessian kheedian