论文标题
无统治的生成模型的统计保证
Statistical guarantees for generative models without domination
论文作者
论文摘要
在本文中，我们介绍了一个方便的框架，用于从统计角度研究（对抗性）生成模型。它包括将生成设备建模为尺寸的单位超立方体的平滑转换，该维度比环境空间小得多，并通过积分概率度量来测量生成模型的质量。在通过平滑度类别定义的集成概率度量的特定情况下，我们建立了一个风险结合，以量化各种参数的作用。特别是，它清楚地显示了降低对生成模型误差的影响。
In this paper, we introduce a convenient framework for studying (adversarial) generative models from a statistical perspective. It consists in modeling the generative device as a smooth transformation of the unit hypercube of a dimension that is much smaller than that of the ambient space and measuring the quality of the generative model by means of an integral probability metric. In the particular case of integral probability metric defined through a smoothness class, we establish a risk bound quantifying the role of various parameters. In particular, it clearly shows the impact of dimension reduction on the error of the generative model.
