Learning to Pass Expectation Propagation Messages

By Nicolas Manfred Otto Heess, Daniel Tarlow, John M. Winn. 2013

49 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages (2015, methodology): “We consider the setting (s1, r1, s2) = (1, 1, 1) which was used in Heess et al. (2013).”
Recurrent Relational Networks (2017, background): “Several works have proposed replacing parts of belief propagation with learned modules [Heess et al., 2013, Lin et al., 2015].”
Just-In-Time Learning for Fast and Flexible Inference (2014, methodology): “However, it also gradually learns to increase the speed of these computations by regressing from input to output messages (in a similar way to [7]) at run-time.”
Distributed Bayesian Learning with Stochastic Natural Gradient Expectation Propagation and the Posterior Server (2015, methodology): “SNEP can therefore be used in place of EP in situations where Monte Carlo moment estimates are used, including graphical models (Heess et al., 2013, Eslami et al., 2014, Jitkrittum et al., 2015, Lienart et al., 2015), hierarchical Bayesian models (Gelman et al., 2014), and approximate Bayesian…”
Stochastic Expectation Propagation (2015, background): “ta problems: the locality of computation make the algorithm simple to parallelise and distribute, and good practical performance on a range of small data applications suggest that it will be accurate [9, 10, 11]. However the elegance of local computation has been bought at the price of prohibitive m”
Applications of Probabilistic Programming (Master's thesis, 2015) (2016, background): “Methods to learn EP operators for inference in Infer.NET have included neural networks (Heess et al., 2013), just-in-time random forests (Eslami et al., 2014) and just-in-time kernel-based regression (Jitkrittum et al., 2015).”
Inference in Probabilistic Graphical Models by Graph Neural Networks (2018, background): “[10] proposes to train a neural network that learns to map message inputs to message outputs for each message operation needed for Expectation Propagation inference, and [11] suggests learning CNNs for estimating factor-to-variable messages in a message-passing procedure.”
Inference Networks for Sequential Monte Carlo in Graphical Models (2016, background): “…models in which closed-form full conditionals are not available (Stuhlmüller et al., 2013), using pre-trained neural networks to inform local MCMC proposal kernels (Jampani et al., 2015; Kulkarni et al., 2015), and learning messages for new factors for expectation-propagation (Heess et al., 2013).”
Recurrent Relational Networks for Complex Relational Reasoning (2018, background): “Several works have proposed replacing parts of belief propagation with learned modules (Heess et al., 2013; Lin et al., 2015).”