# Neural Variational Inference and Learning in Undirected Graphical Models

arXiv: https://arxiv.org/abs/1711.02679 · HTML: https://mlsanity.com/paper/1711.02679/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2017.

## Built on by (most cited first, 4 of 4)

- [Deep Structured Reactive Planning](https://mlsanity.com/paper/2101.06832/) (2021)
- [Empirical Evaluation of Biased Methods for Alpha Divergence Minimization](https://mlsanity.com/paper/2105.06587/) (2021)
- [Perturb-and-max-product: Sampling and learning in discrete energy-based models](https://mlsanity.com/paper/2111.02458/) (2021)
- [Mixture weights optimisation for Alpha-Divergence Variational Inference](https://mlsanity.com/paper/2106.05114/) (2021)

## Abstract (arXiv)

Many problems in machine learning are naturally expressed in the language of undirected graphical models. Here, we propose black-box learning and inference algorithms for undirected models that optimize a variational approximation to the log-likelihood of the model. Central to our approach is an upper bound on the log-partition function parametrized by a function q that we express as a flexible neural network. Our bound makes it possible to track the partition function during learning, to speed-up sampling, and to train a broad class of hybrid directed/undirected models via a unified variational inference framework. We empirically demonstrate the effectiveness of our method on several popular generative modeling datasets.