AISTATS 2015poster135 citations
Learning Deep Sigmoid Belief Networks with Data Augmentation
Zhe Gan, Ricardo Henao, David Carlson, Lawrence Carin
Abstract
Deep directed generative models are developed. The multi-layered model is designed by stacking sigmoid belief networks, with sparsity-encouraging priors placed on the model parameters. Learning and inference of layer-wise model parameters are implemented in a Bayesian setting. By exploring the idea of data augmentation and introducing auxiliary Polya-Gamma variables, simple and efficient Gibbs sampling and mean-field variational Bayes (VB) inference are implemented. To address large-scale datasets, an online version of VB is also developed. Experimental results are presented for three publicly available datasets: MNIST, Caltech 101 Silhouettes and OCR letters.
BibTeX
@InProceedings{pmlr-v38-gan15,
title = {{Learning Deep Sigmoid Belief Networks with Data Augmentation}},
author = {Gan, Zhe and Henao, Ricardo and Carlson, David and Carin, Lawrence},
booktitle = {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics},
pages = {268--276},
year = {2015},
editor = {Lebanon, Guy and Vishwanathan, S. V. N.},
volume = {38},
series = {Proceedings of Machine Learning Research},
address = {San Diego, California, USA},
month = {09--12 May},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v38/gan15.pdf},
url = {https://proceedings.mlr.press/v38/gan15.html},
abstract = {Deep directed generative models are developed. The multi-layered model is designed by stacking sigmoid belief networks, with sparsity-encouraging priors placed on the model parameters. Learning and inference of layer-wise model parameters are implemented in a Bayesian setting. By exploring the idea of data augmentation and introducing auxiliary Polya-Gamma variables, simple and efficient Gibbs sampling and mean-field variational Bayes (VB) inference are implemented. To address large-scale datasets, an online version of VB is also developed. Experimental results are presented for three publicly available datasets: MNIST, Caltech 101 Silhouettes and OCR letters.}
}