Exact recovery in the Ising blockmodel

We consider the problem associated to recovering the block structure of an Ising model given independent observations on the binary hypercube. This new model, called the Ising blockmodel, is a perturbation of the mean field approximation of the Ising model known as the Curie-Weiss model: the sites a...

Full description

Bibliographic Details
Main Author: Rigollet, Philippe
Other Authors: Massachusetts Institute of Technology. Department of Mathematics
Format: Article
Language:English
Published: Institute of Mathematical Statistics 2020
Online Access:https://hdl.handle.net/1721.1/126719
_version_ 1826190649203884032
author Rigollet, Philippe
author2 Massachusetts Institute of Technology. Department of Mathematics
author_facet Massachusetts Institute of Technology. Department of Mathematics
Rigollet, Philippe
author_sort Rigollet, Philippe
collection MIT
description We consider the problem associated to recovering the block structure of an Ising model given independent observations on the binary hypercube. This new model, called the Ising blockmodel, is a perturbation of the mean field approximation of the Ising model known as the Curie-Weiss model: the sites are partitioned into two blocks of equal size and the interaction between those of the same block is stronger than across blocks, to account for more order within each block. We study probabilistic, statistical and computational aspects of this model in the high-dimensional case when the number of sites may be much larger than the sample size.
first_indexed 2024-09-23T08:43:35Z
format Article
id mit-1721.1/126719
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T08:43:35Z
publishDate 2020
publisher Institute of Mathematical Statistics
record_format dspace
spelling mit-1721.1/1267192020-08-22T03:33:50Z Exact recovery in the Ising blockmodel Rigollet, Philippe Massachusetts Institute of Technology. Department of Mathematics We consider the problem associated to recovering the block structure of an Ising model given independent observations on the binary hypercube. This new model, called the Ising blockmodel, is a perturbation of the mean field approximation of the Ising model known as the Curie-Weiss model: the sites are partitioned into two blocks of equal size and the interaction between those of the same block is stronger than across blocks, to account for more order within each block. We study probabilistic, statistical and computational aspects of this model in the high-dimensional case when the number of sites may be much larger than the sample size. National Science Foundation (U.S.) (Grants DMS-154109, DMS-154110) United States. Defense Advanced Research Projects Agency (Grant DARPA-BAA-16-46) 2020-08-21T13:40:44Z 2020-08-21T13:40:44Z 2017-02 2019-11-19T18:35:06Z Article http://purl.org/eprint/type/JournalArticle 0090-5364 https://hdl.handle.net/1721.1/126719 Berthet, Quentin, Philippe Rigollet and Piyush Srivastava. “Exact recovery in the Ising blockmodel.” The annals of statistics, 47, 4 (February 2019): 1805-1834 © 2019 The Author(s) en 10.1214/17-AOS1620 The annals of statistics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Mathematical Statistics arXiv
spellingShingle Rigollet, Philippe
Exact recovery in the Ising blockmodel
title Exact recovery in the Ising blockmodel
title_full Exact recovery in the Ising blockmodel
title_fullStr Exact recovery in the Ising blockmodel
title_full_unstemmed Exact recovery in the Ising blockmodel
title_short Exact recovery in the Ising blockmodel
title_sort exact recovery in the ising blockmodel
url https://hdl.handle.net/1721.1/126719
work_keys_str_mv AT rigolletphilippe exactrecoveryintheisingblockmodel