English

Iterative Neural Autoregressive Distribution Estimator (NADE-k)

Machine Learning 2014-12-09 v3 Machine Learning

Abstract

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 kk 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.

Keywords

Cite

@article{arxiv.1406.1485,
  title  = {Iterative Neural Autoregressive Distribution Estimator (NADE-k)},
  author = {Tapani Raiko and Li Yao and Kyunghyun Cho and Yoshua Bengio},
  journal= {arXiv preprint arXiv:1406.1485},
  year   = {2014}
}

Comments

Accepted at Neural Information Processing Systems (NIPS) 2014

R2 v1 2026-06-22T04:32:01.142Z