Search Machine Learning Repository: @inproceedings{icml2014c2_mnih14,
    Publisher = {JMLR Workshop and Conference Proceedings},
    Title = {Neural Variational Inference and Learning in Belief Networks},
    Url = {http://jmlr.org/proceedings/papers/v32/mnih14.pdf},
    Abstract = {Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well. We propose a fast non-iterative approximate inference method that uses a feedforward network to implement efficient exact sampling from the variational posterior. The model and this inference network are trained jointly by maximizing a variational lower bound on the log-likelihood. Although the naive estimator of the inference network gradient is too high-variance to be useful, we make it practical by applying several straightforward model-independent variance reduction techniques. Applying our approach to training sigmoid belief networks and deep autoregressive networks, we show that it outperforms the wake-sleep algorithm on MNIST and achieves state-of-the-art results on the Reuters RCV1 document dataset.},
    Author = {Andriy Mnih and Karol Gregor},
    Editor = {Tony Jebara and Eric P. Xing},
    Year = {2014},
    Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
    Pages = {1791-1799}
   }