arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.00628cs.LGstat.ML
收藏

用精确-回忆偏差训练规范化流

Training Normalizing Flows with the Precision-Recall Divergence

LAMSADE(拉马萨德实验室);CNRS(法国国家科学研究中心);Université Paris-Dauphine-PSL(巴黎多芬大学-巴黎文理研究大学)

Alexandre Verine, Benjamin Negrevergne, Muni Sreenivas Pydi, Yann Chevaleyre

摘要:

生成模型可能具有不同的故障模式,如模式丢弃和低质量样本,这无法通过单个标量度量来捕获。为了解决这个问题,最近的工作提出了使用精度和召回率来评估生成模型,其中精度测量样本的质量,召回率测量目标分布的覆盖范围。尽管目标和估计分布之间的各种差异度量用于训练生成模型,但尚不清楚差异度量的各种选择会实现什么精确度-召回权衡。在本文中,我们表明,实现一个指定的精度召回权衡对应于最小化的分歧,从一个家庭,我们称之为{ \em PR分歧}。相反,任何偏差都可以被写为PR偏差的线性组合,因此对应于最小化加权的准确率-召回率权衡。此外,我们提出了一种新的生成模型,能够训练一个规范化的流程,以尽量减少任何分歧,特别是,实现了给定的精度召回权衡。

英文摘要:

Generative models can have distinct mode of failures like mode dropping and low quality samples, which cannot be captured by a single scalar metric. To address this, recent works propose evaluating generative models using precision and recall, where precision measures quality of samples and recall measures the coverage of the target distribution. Although a variety of discrepancy measures between the target and estimated distribution are used to train generative models, it is unclear what precision-recall trade-offs are achieved by various choices of the discrepancy measures. In this paper, we show that achieving a specified precision-recall trade-off corresponds to minimising -divergences from a family we call the {\em PR-divergences }. Conversely, any -divergence can be written as a linear combination of PR-divergences and therefore correspond to minimising a weighted precision-recall trade-off. Further, we propose a novel generative model that is able to train a normalizing flow to minimise any -divergence, and in particular, achieve a given precision-recall trade-off.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑