# Iterative Neural Autoregressive Distribution Estimator (NADE-k)

arXiv: https://arxiv.org/abs/1406.1485 · HTML: https://mlsanity.com/paper/1406.1485/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2014.

## Built on by (most cited first, 1 of 1)

- [Generative modeling with projected entangled-pair states](https://mlsanity.com/paper/2202.08177/) (2022)

## Abstract (arXiv)

Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple steps, arguing that it is easier to learn to improve a reconstruction in k steps rather than to learn to reconstruct in a single inference step. The proposed model is an unsupervised building block for deep learning that combines the desirable properties of NADE and multi-predictive training: (1) Its test likelihood can be computed analytically, (2) it is easy to generate independent samples from it, and (3) it uses an inference engine that is a superset of variational inference for Boltzmann machines. The proposed NADE-k is competitive with the state-of-the-art in density estimation on the two datasets tested.