论文标题
RBM-Flow和D-Flow：具有离散能量基础空间的可逆流
RBM-Flow and D-Flow: Invertible Flows with Discrete Energy Base Spaces
论文作者
论文摘要
可以使用经过训练的可逆流（如果）来实现复杂数据分布的有效采样，在这种情况下，通过通过多种非线性双线徒转换来推动简单的基本分布来生成模型分布。但是，IFS中转换的迭代性质可能会限制目标分布的近似值。在本文中，我们试图通过实现RBM-Flow来减轻这种情况，RBM-Flow是一种基本分布的IF模型，它是限制性的Boltzmann机器（RBM），并施加了连续的平滑。我们表明，通过使用RBM-Flow，我们能够提高由IS（IS）和Frechet Inception距离（FID）量化的样品的质量，其基线模型具有相同的IF转换，但表现力较低，但具有较低的基础分布。此外，我们还获得了d-flow，这是具有不相关离散潜在变量的IF模型。我们表明，D-Flow具有相似的可能性，而FID/是典型的IF具有高斯基础变量的分数，但是具有额外的好处，即全局特征被有意义地编码为潜在空间中的离散标签。
Efficient sampling of complex data distributions can be achieved using trained invertible flows (IF), where the model distribution is generated by pushing a simple base distribution through multiple non-linear bijective transformations. However, the iterative nature of the transformations in IFs can limit the approximation to the target distribution. In this paper we seek to mitigate this by implementing RBM-Flow, an IF model whose base distribution is a Restricted Boltzmann Machine (RBM) with a continuous smoothing applied. We show that by using RBM-Flow we are able to improve the quality of samples generated, quantified by the Inception Scores (IS) and Frechet Inception Distance (FID), over baseline models with the same IF transformations, but with less expressive base distributions. Furthermore, we also obtain D-Flow, an IF model with uncorrelated discrete latent variables. We show that D-Flow achieves similar likelihoods and FID/IS scores to those of a typical IF with Gaussian base variables, but with the additional benefit that global features are meaningfully encoded as discrete labels in the latent space.
