# Neural Variational Inference and Learning in Belief Networks

arXiv: https://arxiv.org/abs/1402.0030 · HTML: https://mlsanity.com/paper/1402.0030/

## Key facts

- Cited by 117 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2014.

## Built on by (most cited first, 30 of 117)

- [Trajectory balance: Improved credit assignment in GFlowNets](https://mlsanity.com/paper/2201.13259/) (2022)
- [GFlowNets and variational inference](https://mlsanity.com/paper/2210.00580/) (2022)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting](https://mlsanity.com/paper/2206.00761/) (2022)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks](https://mlsanity.com/paper/2111.01564/) (2021)
- [A safety realignment framework via subspace-oriented model fusion for large language models](https://mlsanity.com/paper/2405.09055/) (2024)
- [Recent Advances for Quantum Neural Networks in Generative Learning](https://mlsanity.com/paper/2206.03066/) (2022)
- [Neural Methods for Amortized Inference](https://mlsanity.com/paper/2404.12484/) (2024)
- [FoveaTer: Foveated Transformer for Image Classification](https://mlsanity.com/paper/2105.14173/) (2021)
- [AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning](https://mlsanity.com/paper/2205.15319/) (2022)
- [Consistent Sparse Deep Learning: Theory and Computation](https://mlsanity.com/paper/2102.13229/) (2021)
- [Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning](https://mlsanity.com/paper/2104.09122/) (2021)
- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [Learning Opinion Summarizers by Selecting Informative Reviews](https://mlsanity.com/paper/2109.04325/) (2021)
- [Gradient Estimation with Discrete Stein Operators](https://mlsanity.com/paper/2202.09497/) (2022)
- [Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows](https://mlsanity.com/paper/2207.08219/) (2022)
- [Sparse Graph Learning from Spatiotemporal Time Series](https://mlsanity.com/paper/2205.13492/) (2022)
- [Estimating Conditional Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2306.03301/) (2023)
- [MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control](https://mlsanity.com/paper/2508.10684/) (2025)
- [Guiding Visual Question Generation](https://mlsanity.com/paper/2110.08226/) (2021)
- [Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick](https://mlsanity.com/paper/2311.12569/) (2023)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Storchastic: A Framework for General Stochastic Automatic Differentiation](https://mlsanity.com/paper/2104.00428/) (2021)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints](https://mlsanity.com/paper/2112.03568/) (2021)
- [Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments](https://mlsanity.com/paper/2311.04453/) (2023)
- [Neuro-Symbolic AI: Explainability, Challenges, and Future Trends](https://mlsanity.com/paper/2411.04383/) (2024)
- [ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables](https://mlsanity.com/paper/2105.14141/) (2021)

## Abstract (arXiv)

Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well. We propose a fast non-iterative approximate inference method that uses a feedforward network to implement efficient exact sampling from the variational posterior. The model and this inference network are trained jointly by maximizing a variational lower bound on the log-likelihood. Although the naive estimator of the inference model gradient is too high-variance to be useful, we make it practical by applying several straightforward model-independent variance reduction techniques. Applying our approach to training sigmoid belief networks and deep autoregressive networks, we show that it outperforms the wake-sleep algorithm on MNIST and achieves state-of-the-art results on the Reuters RCV1 document dataset.