Title :
Dual Optimality Frameworks for Expectation Propagation
Author :
Walsh, John MacLaren
Author_Institution :
Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY
Abstract :
We show a duality relationship between two different optimality frameworks for expectation propagation, a family of algorithms for distributed statistical inference that include belief propagation and the turbo decoder/equalizer as particular examples. Each of the two optimality frameworks may then be used to interpret each other
Keywords :
belief maintenance; decoding; duality (mathematics); equalisers; inference mechanisms; statistical analysis; turbo codes; belief propagation; distributed statistical inference; dual optimality frameworks; duality relationship; expectation propagation; turbo decoder; turbo equalizer; Belief propagation; Density measurement; Equalizers; Inference algorithms; Iterative algorithms; Maximum likelihood decoding; Parity check codes; Particle measurements; Probability density function; Statistics;
Conference_Titel :
Signal Processing Advances in Wireless Communications, 2006. SPAWC '06. IEEE 7th Workshop on
Conference_Location :
Cannes
Print_ISBN :
0-7803-9710-X
Electronic_ISBN :
0-7803-9711-8
DOI :
10.1109/SPAWC.2006.346483
