Download:
|
by Yair Weiss, William T. Freeman
Neural Computation
http://www.cs.berkeley.edu/~yweiss/gaussTR.ps.gz
Add To MetaCart
Abstract:
Graphical models, such as Bayesian networks and Markov Random Fields represent statistical dependencies of variables by a graph. Local "belief propagation " rules of the sort proposed by Pearl [18] are guaranteed to converge to the correct posterior probabilities in singly connected graphical models. Recently, a number of researchers have empirically demonstrated good performance of "loopy belief propagation"--using these same rules on graphs with loops. Perhaps the most dramatic instance is the near Shannonlimit performance of "Turbo codes", whose decoding algorithm is equivalent to loopy belief propagation. Except for the case of graphs with a single loop, there has been little theoretical understanding of the performance of loopy propagation. Here we analyze belief propagation in networks with arbitrary topologies when the nodes in the graph describe jointly Gaussian
Citations
|
4387
|
Probabilistic Reasoning in Intelligent Systems
– Pearl
- 1988
|
|
2322
|
Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images
– Geman, Geman
- 1984
|
|
788
|
Near Shannon limit error-correcting coding and decoding: turbo codes
– Berrou, Glavieux, et al.
- 1993
|
|
582
|
An Introduction to Bayesian Networks
– Jensen
- 1996
|
|
539
|
Graphical Models
– Lauritzen
- 1996
|
|
200
|
Loopy belief propagation for approximate inference: An empirical study
– Murphy, Weiss, et al.
- 1999
|
|
194
|
Low Density Parity Check Codes
– Gallager
- 1963
|
|
193
|
Turbo decoding as an instance of Pearl’s “belief propagation” algorithm
– McEliece, Mackay, et al.
- 1998
|
|
138
|
Codes and decoding on general graphs
– Wiberg
- 1996
|
|
88
|
Correctness of local probability propagation in graphical models with loops
– Weiss
|
|
78
|
Iterative decoding of compound codes by probability propagation in graphical models, this issue
– Kschischang, Frey
|
|
78
|
Efficient multiscale regularization with applications to the computation of optical flow
– Luettgen, Karl, et al.
- 1994
|
|
49
|
Belief propagation and revision in networks with loops
– Weiss
- 1997
|
|
36
|
The turbo decision algorithm
– McEliece, Rodemich, et al.
- 1995
|
|
31
|
Learning to estimate scenes from images
– Freeman, Pasztor
- 1999
|
|
28
|
On the convergence of iterative decoding on graphs with a single cycle
– Aji, Horn, et al.
- 1998
|
|
28
|
Interpreting images by propagating Bayesian beliefs
– Weiss
- 1997
|
|
24
|
Introduction in Inference in Bayesian Networks
– COWELL
- 1999
|
|
24
|
E cient multiscale regularization with applications to the computation of optical ow
– Luettgen, Karl, et al.
- 1994
|
|
20
|
Introducction to Applied Mathematics. Wellesley Cambridge press
– Strang
- 1986
|
|
17
|
Bayesian networks for pattern classification, data compression, and channel coding
– Frey
- 1997
|
|
14
|
Belief networks, hidden Markov models, and Markov random fields: A unifying view
– Smyth
- 1997
|
|
13
|
The modeling and estimation of statistically self-similar processes in a multiresolution framework
– Daniel, Willsky
- 1999
|
|
8
|
Iterative decoding of tailbiting trellisses. preprint presented at
– Forney, Kschischang, et al.
- 1998
|
|
2
|
Bayesian Networks for Pattern Classi cation, Data Compression and Channel Coding
– Frey
- 1998
|
|
2
|
The generalized distributive law. submitted to
– Aji, McEliece
- 1998
|
|
1
|
Loopy propagation gives the correct posterior means for gaussians
– Weiss, Freeman
- 1999
|
