论文标题
通过堆叠Wasserstein AutoCoders学习深层层次结构
Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
论文作者
论文摘要
具有层次范围可变量结构的概率模型在非自动性，无监督密度的模型中提供了最先进的结果。但是，基于变异自动编码器（VAE）培训此类模型的最常见方法通常无法利用深层层次结构。成功的方法需要复杂的推理和优化方案。最佳运输是一种具有吸引力的理论特性的培训生成模型的替代性，非易于运输的框架，从原则上则可以更轻松地在分布之间进行培训。在这项工作中，我们提出了一种基于最佳运输的深层层次结构的培训模型的新方法，而无需高度定制的模型和推理网络。我们表明，我们的方法使生成模型能够充分利用其深层层次结构，避免了VAE的众所周知的“潜在可变崩溃”问题；因此，与原始的Wasserstein AutoCododer相比，具有最大的平均差异差异的原始样本代表质量上的样本世代和更容易解释的潜在表示。
Probabilistic models with hierarchical-latent-variable structures provide state-of-the-art results amongst non-autoregressive, unsupervised density-based models. However, the most common approach to training such models based on Variational Autoencoders (VAEs) often fails to leverage deep-latent hierarchies; successful approaches require complex inference and optimisation schemes. Optimal Transport is an alternative, non-likelihood-based framework for training generative models with appealing theoretical properties, in principle allowing easier training convergence between distributions. In this work we propose a novel approach to training models with deep-latent hierarchies based on Optimal Transport, without the need for highly bespoke models and inference networks. We show that our method enables the generative model to fully leverage its deep-latent hierarchy, avoiding the well known "latent variable collapse" issue of VAEs; therefore, providing qualitatively better sample generations as well as more interpretable latent representation than the original Wasserstein Autoencoder with Maximum Mean Discrepancy divergence.
