A Universal Marginalizer for Amortized Inference in Generative Models

Multilayer feedforward networks are universal approximators

Kurt Hornik, Maxwell Stinchcombe, and Halbert White · 1989

Earlier work this paper cites.

AIS-BN: An adaptive importance sampling algorithm for evidential reasoning in large Bayesian networks

Jian Cheng and Marek J. Druzdzel · 2000

Earlier work this paper cites.

Recognition networks for approximate inference in bn20 networks

Quaid Morris · 2001

Earlier work this paper cites.

Annealed importance sampling

Radford M Neal · 2001

Earlier work this paper cites.

Any reasonable cost function can be used for a posteriori probability approximation

Marco Saerens, Patrice Latinne, and Christine Decaestecker · 2002

Earlier work this paper cites.

Graphical models, exponential families, and variational inference

Martin J Wainwright, Michael I Jordan, et al · 2008

Cited alongside, same era.

Probabilistic graphical models: principles and techniques

Daphne Koller and Nir Friedman · 2009

Cited alongside, same era.

Amortized inference in probabilistic reasoning

Samuel Gershman and Noah Goodman · 2014

Cited alongside, same era.

Adam: A method for stochastic optimization

Original

Diederik Kingma and Jimmy Ba · 2014

Cited alongside, same era.

Dropout: A simple way to prevent neural networks from overfitting

Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov · 2014

Cited alongside, same era.

MADE: masked autoencoder for distribution estimation

Mathieu Germain, Karol Gregor, Iain Murray, and Hugo Larochelle · 2015

Later among the works it cites.

Neural adaptive sequential monte carlo

Shixiang Gu, Zoubin Ghahramani, and Richard E Turner · 2015

Later among the works it cites.

Inference networks for sequential Monte Carlo in graphical models

Brooks Paige and Frank Wood · 2016

Later among the works it cites.

Using synthetic data to train neural networks is model-based reasoning

Original

Tuan Anh Le, Atilim Gunes Baydin, Robert Zinkov, and Frank Wood · 2017

Closest in time.