Detalle del congreso

Autores: Tianju Sui; Damián Marelli; Minyue Fu.

Resumen: Despite of its wide success in many distributedstatistical learning applications, the well-known Gaussian beliefpropagation (BP) algorithm still lacks sufficient understandingat the theoretical level. This paper studies the convergenceof Gaussian BP by analyzing the dynamic behaviour of themarginal covariances. We show, under a mild technical as-sumption, that the information matrices (i.e., the inverses ofmarginal covariances) are guaranteed to converge exponentiallyto positive-definite matrices. The convergence rate is explicitlycharacterized. This result is a key step to the understanding ofthe dynamic behaviour of the BP iterations.

Tipo de reunión: Conferencia.

Tipo de trabajo: Artículo Completo.

Producción: Convergence Analysis of Gaussian Belief Propagation: Dynamic Behaviour of Marginal Covariances.

Reunión científica: IEEE Conference on on Acoustics, Speech, and Signal Processing (ICASSP).

Lugar: Shanghai.

Institución organizadora: Institute of Electrical and Electronics Engineers (IEEE).

Publicado: Sí

Lugar publicación: Nueva York

Mes de reunión: 3

Año: 2016.