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 …
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
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 …
submatrix of elevated mean µ in a large n× n symmetric matrix subject to additive standard …
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 …
model, for the special case of two non-overlapping symmetric communities. This gives raise …
Achieving optimal misclassification proportion in stochastic block models
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 …
paper, we present a polynomial time two-stage method that provably achieves optimal …
Tensor SVD: Statistical and computational limits
In this paper, we propose a general framework for tensor singular value decomposition
(tensor singular value decomposition (SVD)), which focuses on the methodology and theory …
(tensor singular value decomposition (SVD)), which focuses on the methodology and theory …
Achieving exact cluster recovery threshold via semidefinite programming
The binary symmetric stochastic block model deals with a random graph of n vertices
partitioned into two equal-sized clusters, such that each pair of vertices is independently …
partitioned into two equal-sized clusters, such that each pair of vertices is independently …
Minimax rates of community detection in stochastic block models
Supplement to “Mimimax rates of community detection in stochastic block models”. In the
supplement 31, we provide proofs of Lemma 5.2, Propositions 5.1 and 5.2. We also provide …
supplement 31, we provide proofs of Lemma 5.2, Propositions 5.1 and 5.2. We also provide …
Community detection in sparse networks via Grothendieck's inequality
O Guédon, R Vershynin - Probability Theory and Related Fields, 2016 - Springer
We present a simple and flexible method to prove consistency of semidefinite optimization
problems on random graphs. The method is based on Grothendieck's inequality. Unlike the …
problems on random graphs. The method is based on Grothendieck's inequality. Unlike the …
On semidefinite relaxations for the block model
On semidefinite relaxations for the block model Page 1 The Annals of Statistics 2018, Vol. 46,
No. 1, 149–179 https://doi.org/10.1214/17-AOS1545 © Institute of Mathematical Statistics …
No. 1, 149–179 https://doi.org/10.1214/17-AOS1545 © Institute of Mathematical Statistics …
Semidefinite programs on sparse random graphs and their application to community detection
A Montanari, S Sen - Proceedings of the forty-eighth annual ACM …, 2016 - dl.acm.org
Denote by A the adjacency matrix of an Erdos-Renyi graph with bounded average degree.
We consider the problem of maximizing< A-EA, X> over the set of positive semidefinite …
We consider the problem of maximizing< A-EA, X> over the set of positive semidefinite …