论文标题
切成薄片的范围标准化流量：超出最大似然训练
Sliced-Wasserstein normalizing flows: beyond maximum likelihood training
论文作者
论文摘要
尽管有优势，但正常化的流量通常会遇到几个缺点，包括它们产生不现实数据（例如图像）的趋势及其无法检测到分布数据的数据。这些缺陷的原因之一在于培训策略，传统上仅利用最大可能性原则。本文提出了一个新的训练范式，该训练范式基于结合最大似然原理（MLE）和切成薄片的距离的混合物镜功能。在合成玩具示例和真实图像数据集上获得的结果在生成样品的可能性和视觉方面都显示出更好的生成能力。相度地，提出的方法导致分布数据的可能性较低，证明了所得流量的数据保真度更大。
Despite their advantages, normalizing flows generally suffer from several shortcomings including their tendency to generate unrealistic data (e.g., images) and their failing to detect out-of-distribution data. One reason for these deficiencies lies in the training strategy which traditionally exploits a maximum likelihood principle only. This paper proposes a new training paradigm based on a hybrid objective function combining the maximum likelihood principle (MLE) and a sliced-Wasserstein distance. Results obtained on synthetic toy examples and real image data sets show better generative abilities in terms of both likelihood and visual aspects of the generated samples. Reciprocally, the proposed approach leads to a lower likelihood of out-of-distribution data, demonstrating a greater data fidelity of the resulting flows.
