Timezone: »
Poster
An Application of Tree-Structured Expectation Propagation for Channel Decoding
Pablo M Olmos · Luis Salamanca · Juan J. Murillo-Fuentes · Fernando Perez-Cruz
We show an application of a tree structure for approximate inference in graphical models using the expectation propagation algorithm. These approximations are typically used over graphs with short-range cycles. We demonstrate that these approximations also help in sparse graphs with long-range loops, as the ones used in coding theory to approach channel capacity. For asymptotically large sparse graph, the expectation propagation algorithm together with the tree structure yields a completely disconnected approximation to the graphical model but, for for finite-length practical sparse graphs, the tree structure approximation to the code graph provides accurate estimates for the marginal of each variable.
Author Information
Pablo M Olmos (Universidad de Sevilla)
Luis Salamanca (University of Sevilla)
Juan J. Murillo-Fuentes (Universidad de Sevilla)
Fernando Perez-Cruz (Swiss Data Science Center (ETH Zurich and EPFL))
More from the Same Authors
-
2018 Poster: Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo »
Marton Havasi · José Miguel Hernández-Lobato · Juan J. Murillo-Fuentes -
2015 Poster: Infinite Factorial Dynamical Model »
Isabel Valera · Francisco Ruiz · Lennart Svensson · Fernando Perez-Cruz -
2012 Poster: Bayesian Nonparametric Modeling of Suicide Attempts »
Francisco Ruiz · Isabel Valera · Carlos Blanco · Fernando Perez-Cruz -
2012 Spotlight: Bayesian Nonparametric Modeling of Suicide Attempts »
Francisco Ruiz · Isabel Valera · Carlos Blanco · Fernando Perez-Cruz -
2009 Mini Symposium: Assistive Machine Learning for People with Disabilities »
Fernando Perez-Cruz · Emilio Parrado-Hernandez · David R Hardoon · Jaisiel Madrid-Sanchez -
2008 Poster: Estimation of Information Theoretic Measures for Continuous Random Variables »
Fernando Perez-Cruz