Title :
Message error analysis of loopy belief propagation
Author :
Shi, Xiangqiong ; Schonfeld, Dan ; Tuninetti, Daniela
Author_Institution :
Electr. & Comput. Eng., Univ. of Illinois at Chicago, Chicago, IL, USA
Abstract :
The loopy belief propagation algorithm (LBP) is known to perform extremely well in many practical problems of probability inference and learning on graphical models, even in presence of multiple loops. Although general necessary conditions for convergence of LBP to a unique fixed point solution are still unknown, various techniques have been explored to understand error propagation when LBP fails to converge. In this paper, we rely on the contractive mapping of message errors to present novel distance bounds between multiple fixed point solutions when LBP does not converge. We give examples of networks where our bounds are tighter than existing ones.
Keywords :
belief networks; error analysis; inference mechanisms; learning (artificial intelligence); contractive mapping; distance bounds; error propagation; graphical model; learning; loopy belief propagation; message error analysis; probability inference; Bayesian methods; Belief propagation; Convergence; Error analysis; Graphical models; Inference algorithms; Random variables; Sufficient conditions; Sum product algorithm; Tree graphs; Bayesian Networks; Error Analysis; Graphical Model; Loopy Belief Propagation; Markov Random Fields;
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2010.5495075