arrow
返回

PROPERTY TESTING IN HIGH-DIMENSIONAL ISING MODELS

delete2019-10-01
delete13
delete
OA
AI
M
Matey Neykov *
H
Han Liu
DOI:10.1214/18-AOS1754delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
This paper explores the information-theoretic limitations of graph property testing in zero-field Ising models. Instead of learning the entire graph structure, sometimes testing a basic graph property such as connectivity, cycle presence or maximum clique size is a more relevant and attainable objective. Since property testing is more fundamental than graph recovery, any necessary conditions for property testing imply corresponding conditions for graph recovery, while custom property tests can be statistically and/or computationally more efficient than graph recovery based algorithms. Understanding the statistical complexity of property testing requires the distinction of ferromagnetic (i.e., positive interactions only) and general Ising models. Using combinatorial constructs such as graph packing and strong monotonicity, we characterize how target properties affect the corresponding minimax upper and lower bounds within the realm of ferromagnets. On the other hand, by studying the detection of an antiferromagnetic (i.e., negative interactions only) Curie-Weiss model buried in Rademacher noise, we show that property testing is strictly more challenging over general Ising models. In terms of methodological development, we propose two types of correlation based tests: computationally efficient screening for ferromagnets, and score type tests for general models, including a fast cycle presence test. Our correlation screening tests match the information-theoretic bounds for property testing in ferromagnets in certain regimes.
Keyword:
Ising models
minimax testing
Dobrushin's comparison theorem
anti-ferromagnetic Curie-Weiss detection
two-point function bounds
correlation tests
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Annals of Statistics 封面图
Annals of Statistics
IF:
3.7
论文数:
2.8K
被引数:
2.9W

机构

C
Carnegie Mellon University
学者数:
1.4W
论文数: 1.4W
被引数: 2.7W
N
Northwestern University
学者数:
6.2W
论文数: 5.3W
被引数: 3.9K
引用论文

引用论文

Emulating Target Clinical Trials of Radical Nephrectomy With or Without Lymph Node Dissection for Renal Cell Carcinoma
err2020-06-01
err0
errOAAI
errJanine Bacic; Tao Liu; R. Houston Thompson; Stephen A. Boorjian; Bradley C. Leibovich; Dragan Golijanin; Boris Gershman
err分享
err收藏
EXACT RECOVERY IN THE ISING BLOCKMODEL
err2019-08-01
err24
errOAAI
errBerthet, Quentin; Rigollet, Philippe; Srivastava, Piyush
err分享
err收藏
High-dimensional graphs and variable selection with the Lasso
err2006-06-01
err2.9K
errOAAI
errMeinshausen, Nicolai; Buehlmann, Peter
err分享
err收藏
Atomic simulation of helium trapping in displacement cascades
err2016-01-01
err0
PREAI
errNengwen Hu; Huiqiu Deng; Canglong Wang; Wangyu Hu
err分享
err收藏
DETECTION OF CORRELATIONS
err2012-02-01
err37
errOAAI
errArias-Castro, Ery; Bubeck, Sebastien; Lugosi, Gabor
err分享
err收藏
Spatial behaviour and population dynamics of woodland rodents
err1998-06-12
err0
errOAAI
errMaria Mazurkiewicz; Ewa Rajska-Jurgiel
err分享
err收藏
ON COMBINATORIAL TESTING PROBLEMS
err2010-10-01
err89
errOAAI
errAddario-Berry, Louigi; Broutin, Nicolas; Devroye, Luc; Lugosi, Gabor
err分享
err收藏
学者 查看更多内容