Exact recovery in block spin Ising models at the critical line

Type: Article

Publication Date: 2020-01-01

Citations: 5

DOI: https://doi.org/10.1214/20-ejs1703

Abstract

We show how to exactly reconstruct the block structure at the critical line in the so-called Ising block model. This model was recently re-introduced by Berthet, Rigollet and Srivastava in [2]. There the authors show how to exactly reconstruct blocks away from the critical line and they give an upper and a lower bound on the number of observations one needs; thereby they establish a minimax optimal rate (up to constants). Our technique relies on a combination of their methods with fluctuation results obtained in [20]. The latter are extended to the full critical regime. We find that the number of necessary observations depends on whether the interaction parameter between two blocks is positive or negative: In the first case, there are about $N\log N$ observations required to exactly recover the block structure, while in the latter case $\sqrt{N}\log N$ observations suffice.

Locations

  • arXiv (Cornell University) - View - PDF
  • Electronic Journal of Statistics - View - PDF

Similar Works

Action Title Year Authors
+ Exact Recovery in Block Spin Ising Models at the Critical Line 2019 Matthias Löwe
Kristina Schubert
+ Exact Recovery in Block Spin Ising Models at the Critical Line. 2019 Matthias Löwe
Kristina Schubert
+ Exact recovery and sharp thresholds of Stochastic Ising Block Model 2020 Min Ye
+ PDF Chat Exact Recovery and Sharp Thresholds of Stochastic Ising Block Model 2021 Min Ye
+ PDF Chat Exact recovery in the Ising blockmodel 2019 Quentin Berthet
Philippe Rigollet
Piyush Srivastava
+ Exact recovery in the Ising blockmodel 2016 Quentin Berthet
Philippe Rigollet
Piyush Srivastava
+ Exact recovery in the Ising blockmodel 2016 Quentin Berthet
Philippe Rigollet
Piyush Srivastava
+ Belief propagation, robust reconstruction and optimal recovery of block models 2016 Elchanan Mossel
Joe Neeman
Allan Sly
+ Belief propagation, robust reconstruction and optimal recovery of block models 2014 Elchanan Mossel
Joe Neeman
Allan Sly
+ Belief propagation, robust reconstruction and optimal recovery of block models 2014 Elchanan Mossel
Joe Neeman
Allan Sly
+ Sample-optimal and efficient learning of tree Ising models 2021 Constantinos Daskalakis
Qinxuan Pan
+ Efficient Exact Sampling for the Ising Model at all Temperatures 2010 Mario Ullrich
+ A SIMPLE Approach to Provably Reconstruct Ising Model with Global Optimality 2023 Junxian Zhu
Xuanyu Chen
Jin Zhu
Xueqin Wang
Heping Zhang
+ Tree-structured Ising models can be learned efficiently. 2020 Constantinos Daskalakis
Qinxuan Pan
+ Efficiently learning Ising models on arbitrary graphs 2014 Guy Bresler
+ Efficiently learning Ising models on arbitrary graphs 2014 Guy Bresler
+ Fluctuations for block spin Ising models 2018 Matthias Löwe
Kristina Schubert
+ Approximate Recovery Of Ising Models with Side Information 2020 Saurabh Sihag
Ali Tajer
+ Stochastic Block Models and Reconstruction 2012 Elchanan Mossel
Joe Neeman
Allan Sly
+ Sample-Optimal and Efficient Learning of Tree Ising models 2020 Constantinos Daskalakis
Qinxuan Pan