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 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-prediction 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.
Original language | English (US) |
---|---|
Pages (from-to) | 325-333 |
Number of pages | 9 |
Journal | Advances in Neural Information Processing Systems |
Volume | 1 |
Issue number | January |
State | Published - 2014 |
Event | 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada Duration: Dec 8 2014 → Dec 13 2014 |
ASJC Scopus subject areas
- Computer Networks and Communications
- Information Systems
- Signal Processing