In this article we revisit the definition of Precision-Recall (PR) curves for
generative models proposed by Sajjadi et al. (arXiv:1806.00035). Rather than
providing a scalar for generative quality, PR curves distinguish mode-collapse
(poor recall) and bad quality (poor precision). We first generalize their
formulation to arbitrary measures, hence removing any restriction to finite
support. We also expose a bridge between PR curves and type I and type II error
rates of likelihood ratio classifiers on the task of discriminating between
samples of the two distributions. Building upon this new perspective, we
propose a novel algorithm to approximate precision-recall curves, that shares
some interesting methodological properties with the hypothesis testing
technique from Lopez-Paz et al (arXiv:1610.06545). We demonstrate the interest
of the proposed formulation over the original approach on controlled
multi-modal datasets.

重新定义 Sajjadi 等人提出的生成模型的 Precision-Recall curves，推广到任意度量，建立 PR curves 和似然比分类器的 type I 和 type II error rates 之间的联系，并提出新算法近似 PR curves，证明该算法在受控多模态数据集上优于原始方法。