Advanced search
Start date
Betweenand

Statistical mechanics, inference and message-passing algorithms

Grant number: 13/01213-8
Support Opportunities:Scholarships abroad - Research Internship - Doctorate
Effective date (Start): September 09, 2013
Effective date (End): March 08, 2014
Field of knowledge:Physical Sciences and Mathematics - Physics - General Physics
Principal Investigator:Renato Vicente
Grantee:Antonio Andre Monteiro Manoel
Supervisor: Florent Krzakala
Host Institution: Instituto de Física (IF). Universidade de São Paulo (USP). São Paulo , SP, Brazil
Research place: ParisTech, France  
Associated to the scholarship:12/12363-8 - Statistical Mechanics of Steganographic Systems, BP.DR

Abstract

Bayesian inference models are specially useful in the description of processes in which, from noise-corrupted measurements, one wishes to estimate the systems current state. In the last decades, tools from the statistical mechanics of disordered systems have been used in the study of such models; in particular, in the last few years, it has been noted a great similarity between the cavity method and computational techniques known as message-passing algorithms. Such similarity allows for a theoretical analysis of the algorithms performance, as well of properties intrinsic to the inference model. We propose here to study this connection deeper, and to apply both the techniques in the study of specific models. (AU)

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Please report errors in scientific publications list by writing to: cdi@fapesp.br.