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 2201.12245cs.LGstat.ML
收藏

重心估计的Wasserstein迭代网络

Wasserstein Iterative Networks for Barycenter Estimation

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);Artificial Intelligence Research Institute(人工智能研究院);Massachusetts Institute of Technology(麻省理工学院)

Alexander Korotin, Vage Egiazarian, Lingxiao Li, Evgeny Burnaev

摘要:

Wasserstein重心已经变得流行,因为它们能够以几何意义的方式表示概率度量的平均值。在本文中,我们提出了一个算法来近似的Wasserstein-2重心的连续措施,通过生成模型。以前的方法依赖于正则化(熵/二次),这会引入偏差,或者依赖于输入凸神经网络,这对于大规模任务来说不够表达。相比之下,我们的算法不引入偏见,并允许使用任意的神经网络。此外,基于名人面孔数据集,我们构建了Ave,celeba!数据集,可用于通过使用生成模型(如FID)的标准度量对重心算法进行定量评估。

英文摘要:

Wasserstein barycenters have become popular due to their ability to represent the average of probability measures in a geometrically meaningful way. In this paper, we present an algorithm to approximate the Wasserstein-2 barycenters of continuous measures via a generative model. Previous approaches rely on regularization (entropic/quadratic) which introduces bias or on input convex neural networks which are not expressive enough for large-scale tasks. In contrast, our algorithm does not introduce bias and allows using arbitrary neural networks. In addition, based on the celebrity faces dataset, we construct Ave, celeba! dataset which can be used for quantitative evaluation of barycenter algorithms by using standard metrics of generative models such as FID.

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。

↑