聖塔非研究所

摘要 The nonbacktracking operator for a graph is the a

2015-04-17 · 已發表論文 · 更新 2026/08/30 下午12:48

摘要 The nonbacktracking operator for a graph is the adjacency matrix defined on directed edges of the graph. The operator was recently shown to perform optimally in spectral clustering in spa…

本頁只刊出中文翻譯與中文說明;英文原文請見下方原文連結。

原文連結

論文資訊

  • 類型:已發表論文
  • 日期:2015-04-17

摘要

The nonbacktracking operator for a graph is the adjacency matrix defined on directed edges of the graph. The operator was recently shown to perform optimally in spectral clustering in sparse synthetic graphs and have a deep connection to belief propagation algorithm. In this paper we consider nonbacktracking operator for Ising模型 on a general graph with a general coupling distribution and study the spectrum of this operator analytically. We show that spectral algorithms based on this operator is equivalent to belief propagation algorithm linearized at the paramagnetic fixed point and recovers replica-symmetry results on phase boundaries obtained by replica methods. This operator can be applied directly to systems with multiple states like Hopfield model. We show that spectrum of the operato

※ 此為已發表論文,全文需透過期刊付費取得