Community detection and stochastic block models: recent developments

E Abbe - Journal of Machine Learning Research, 2018 - jmlr.org
The stochastic block model (SBM) is a random graph model with planted clusters. It is widely
employed as a canonical model to study clustering and community detection, and provides …

Quantized neural networks: Training neural networks with low precision weights and activations

I Hubara, M Courbariaux, D Soudry, R El-Yaniv… - Journal of Machine …, 2018 - jmlr.org
The principal submatrix localization problem deals with recovering a K× K principal
submatrix of elevated mean µ in a large n× n symmetric matrix subject to additive standard …

Spectral methods for data science: A statistical perspective

Y Chen, Y Chi, J Fan, C Ma - Foundations and Trends® in …, 2021 - nowpublishers.com
Spectral methods have emerged as a simple yet surprisingly effective approach for
extracting information from massive, noisy and incomplete data. In a nutshell, spectral …

Convex relaxation methods for community detection

X Li, Y Chen, J Xu - 2021 - projecteuclid.org
This paper surveys recent theoretical advances in convex optimization approaches for
community detection. We introduce some important theoretical techniques and results for …

[HTML][HTML] Entrywise eigenvector analysis of random matrices with low expected rank

E Abbe, J Fan, K Wang, Y Zhong - Annals of statistics, 2020 - ncbi.nlm.nih.gov
Recovering low-rank structures via eigenvector perturbation analysis is a common problem
in statistical machine learning, such as in factor analysis, community detection, ranking …

Exact recovery in the stochastic block model

E Abbe, AS Bandeira, G Hall - IEEE Transactions on …, 2015 - ieeexplore.ieee.org
The stochastic block model with two communities, or equivalently the planted bisection
model, is a popular model of random graph exhibiting a cluster behavior. In the symmetric …

Community detection in general stochastic block models: Fundamental limits and efficient algorithms for recovery

E Abbe, C Sandon - 2015 IEEE 56th Annual Symposium on …, 2015 - ieeexplore.ieee.org
New phase transition phenomena have recently been discovered for the stochastic block
model, for the special case of two non-overlapping symmetric communities. This gives raise …

A neural collapse perspective on feature evolution in graph neural networks

V Kothapalli, T Tirer, J Bruna - Advances in Neural …, 2024 - proceedings.neurips.cc
Graph neural networks (GNNs) have become increasingly popular for classification tasks on
graph-structured data. Yet, the interplay between graph topology and feature evolution in …

Achieving optimal misclassification proportion in stochastic block models

C Gao, Z Ma, AY Zhang, HH Zhou - Journal of Machine Learning Research, 2017 - jmlr.org
Community detection is a fundamental statistical problem in network data analysis. In this
paper, we present a polynomial time two-stage method that provably achieves optimal …

Rate-optimal graphon estimation

C Gao, Y Lu, HH Zhou - 2015 - projecteuclid.org
Rate-optimal graphon estimation Page 1 The Annals of Statistics 2015, Vol. 43, No. 6, 2624–2652
DOI: 10.1214/15-AOS1354 © Institute of Mathematical Statistics, 2015 RATE-OPTIMAL …