首页    期刊浏览 2024年12月05日 星期四
登录注册

文章基本信息

  • 标题:Phase transitions in semidefinite relaxations
  • 本地全文:下载
  • 作者:Adel Javanmard ; Andrea Montanari ; Federico Ricci-Tersenghi
  • 期刊名称:Proceedings of the National Academy of Sciences
  • 印刷版ISSN:0027-8424
  • 电子版ISSN:1091-6490
  • 出版年度:2016
  • 卷号:113
  • 期号:16
  • 页码:E2218-E2223
  • DOI:10.1073/pnas.1523097113
  • 语种:English
  • 出版社:The National Academy of Sciences of the United States of America
  • 摘要:Statistical inference problems arising within signal processing, data mining, and machine learning naturally give rise to hard combinatorial optimization problems. These problems become intractable when the dimensionality of the data is large, as is often the case for modern datasets. A popular idea is to construct convex relaxations of these combinatorial problems, which can be solved efficiently for large-scale datasets. Semidefinite programming (SDP) relaxations are among the most powerful methods in this family and are surprisingly well suited for a broad range of problems where data take the form of matrices or graphs. It has been observed several times that when the statistical noise is small enough, SDP relaxations correctly detect the underlying combinatorial structures. In this paper we develop asymptotic predictions for several detection thresholds, as well as for the estimation error above these thresholds. We study some classical SDP relaxations for statistical problems motivated by graph synchronization and community detection in networks. We map these optimization problems to statistical mechanics models with vector spins and use nonrigorous techniques from statistical mechanics to characterize the corresponding phase transitions. Our results clarify the effectiveness of SDP relaxations in solving high-dimensional statistical problems.
  • 关键词:semidefinite programming ; phase transitions ; synchronization ; community detection
国家哲学社会科学文献中心版权所有