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 the inference model 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.

我们提出了一种快速的非迭代近似推理方法，通过前馈网络实现从变分后验进行有效精确抽样，该方法通过应用几种直观的模型独立方差减少技术，优于 MNIST 和 Reuters RCV1 文件数据集上的唤醒-睡眠算法，并取得了最新成果。

信念网络中的神经变分推断和学习