Deep generative models parameterized by neural networks have recently
achieved state-of-the-art performance in unsupervised and semi-supervised
learning. We extend deep generative models with auxiliary variables which
improves the variational approximation. The auxiliary variables leave the
generative model unchanged but make the variational distribution more
expressive. Inspired by the structure of the auxiliary variable we also propose
a model with two stochastic layers and skip connections. Our findings suggest
that more expressive and properly specified deep generative models converge
faster with better results. We show state-of-the-art performance within
semi-supervised learning on MNIST, SVHN and NORB datasets.

通过引入辅助变量（auxiliary variables），我们扩展了深度生成模型，用于提高变分近似方法，这让变分分布更有表现力，具有更快的收敛速度和更好的结果，从而实现了半监督学习的最先进性能，适用于 MNIST、SVHN 和 NORB 数据集。

辅助深度生成模型

Auxiliary Deep Generative Models

Variational Autoencoders are powerful models for unsupervised learning.
However deep models with several layers of dependent stochastic variables are
difficult to train which limits the improvements obtained using these highly
expressive models. We propose a new inference model, the Ladder Variational
Autoencoder, that recursively corrects the generative distribution by a data
dependent approximate likelihood in a process resembling the recently proposed
Ladder Network. We show that this model provides state of the art predictive
log-likelihood and tighter log-likelihood lower bound compared to the purely
bottom-up inference in layered Variational Autoencoders and other generative
models. We provide a detailed analysis of the learned hierarchical latent
representation and show that our new inference model is qualitatively different
and utilizes a deeper more distributed hierarchy of latent variables. Finally,
we observe that batch normalization and deterministic warm-up (gradually
turning on the KL-term) are crucial for training variational models with many
stochastic layers.

本文提出了一种新的推断模型 ——“阶梯式变分自动编码器”，并利用逐步添加的近似似然校正生成分布，在生成模型中实现了更深更分布的隐变量层次结构，提供了前沿的预测性能和更紧的下界。