An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model (Q393708): Difference between revisions

From MaRDI portal
Importer (talk | contribs)
Changed an Item
ReferenceBot (talk | contribs)
Changed an Item
 
Property / cites work
 
Property / cites work: The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing / rank
 
Normal rank
Property / cites work
 
Property / cites work: Universality in polytope phase transitions and message passing algorithms / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3997990 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4237477 / rank
 
Normal rank
Property / cites work
 
Property / cites work: The Sherrington-Kirkpatrick Model / rank
 
Normal rank
Property / cites work
 
Property / cites work: Construction of pure states in mean field models for spin glasses / rank
 
Normal rank
Property / cites work
 
Property / cites work: The Parisi formula / rank
 
Normal rank

Latest revision as of 07:09, 7 July 2024

scientific article
Language Label Description Also known as
English
An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model
scientific article

    Statements

    An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model (English)
    0 references
    0 references
    24 January 2014
    0 references
    This paper is devoted to considerations regarding an iterative scheme for solutions of TAP-equations in the Sherrington-Kirkpatrick model. The main idea is based on a representation of iterations which reveals an interesting structureand which does not depend on the temperature parameter. The validity of TAP equations is proved for the high temperatures case; they are valid in low temperatures, but there are many solutions, one is forced to take Gibbs expectation inside ``pure states''. After the introduction, where the author shows all necessary basic information, in Section 2, we have a presentation of the proposed recursive scheme. This presentation ends with the need of a proof that COND(\(J\))=COND(\(J+1\)). This is one of the most important issues in this paper. The rest of the paper (especially Section 4 and Section 5) is devoted to the proof.
    0 references
    0 references
    TAP equations
    0 references
    iterative scheme
    0 references
    Sherrington-Kirkpatrick model
    0 references
    0 references
    0 references