DSpace About DSpace Software

SEIKEI University Repository >
01:紀要(Bulletin) >
09:理工学研究報告 >
第55巻第2号 >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10928/1132

Title: Tree-reweighted近似によるIsing逆問題の解
Other Titles: A Solution to the Inverse Ising Problem in Tree-reweighted Approximation
Authors: 佐野, 崇
Sano, Takashi
Keywords: Ising model
Inverse Ising problem
Bethe approximation
Tree-reweighted approximation
Issue Date: 1-Dec-2018
Publisher: 成蹊大学理工学部
Abstract: To develop an efficient and accurate method for learning in the Ising model, we apply the tree-reweighted approximation to compute the partition function. Using the tree-reweighted approximation, we can optimize the rigorous lower bound of the exact objective function. By solving the moment-matching and self-consistency conditions analytically, we can derive the interaction matrix as a function of the given data statistics. With this solution, we can obtain the optimal interaction matrix without iterative computation. To evaluate the accuracy of the proposed inverse formula, we compared our results to those obtained by existing inverse formulae obtained by other approximations. In an experiment to reconstruct the interaction matrix, we found that the proposed formula returns the best estimates in strongly-attractive regions for various graph structures.
URI: http://hdl.handle.net/10928/1132
Appears in Collections:第55巻第2号

Files in This Item:

File Description SizeFormat
rikougaku-55-2_19-22.pdf696.32 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback