Presentation | 2006-06-16 A method for searching local mimimum of free energy for which convergence is guaranteed. Yukinori TONOSAKI, Yoshiyuki KABASHIMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We investigate a method to search extensively many local minimum of an approximate free energy, which has been known as a technically difficult task. The proposed local search algorithm guarantees convergence to a local minimum of free energy when diagonal components of the Hessian of the given free energy are always positive. The method is applied to analysis of the 3-body spin glass model of low temperature. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | probablistic information processing / free enegy / spin glass |
Paper # | NC2006-27 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2006/6/9(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A method for searching local mimimum of free energy for which convergence is guaranteed. |
Sub Title (in English) | |
Keyword(1) | probablistic information processing |
Keyword(2) | free enegy |
Keyword(3) | spin glass |
1st Author's Name | Yukinori TONOSAKI |
1st Author's Affiliation | Department of Computational Intelligence and System Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology() |
2nd Author's Name | Yoshiyuki KABASHIMA |
2nd Author's Affiliation | Department of Computational Intelligence and System Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology |
Date | 2006-06-16 |
Paper # | NC2006-27 |
Volume (vol) | vol.106 |
Number (no) | 102 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |