Improved message passing for inference in densely connected systemsJ. P. Neirotti and D. Saad
The Neural Computing Research Group, Aston University - Birmingham B4 7ET, UK
received 1 April 2005; accepted in final form 28 June 2005
published online 29 July 2005
An improved inference method for densely connected systems is presented. The approach is based on passing condensed messages between variables, representing macroscopic averages of microscopic messages. We extend previous work that showed promising results in cases where the solution space is contiguous to cases where fragmentation occurs. We apply the method to the signal detection problem of Code Division Multiple Access (CDMA) for demonstrating its potential. A highly efficient practical algorithm is also derived on the basis of insight gained from the analysis.
89.70.+c - Information theory and communication theory.
75.10.Nr - Spin-glass and other random models.
64.60.Cn - Order-disorder transformations; statistical mechanics of model systems.
© EDP Sciences 2005