论文标题
Wasserstein迭代网络用于Barycenter估计
Wasserstein Iterative Networks for Barycenter Estimation
论文作者
论文摘要
Wasserstein Barycenters由于能够以几何有意义的方式代表概率度量的平均值，因此变得流行。在本文中，我们提出了一种算法，以通过生成模型近似连续测量的Wasserstein-2 Barycenters。以前的方法依赖于引入偏见或输入凸神经网络的正则化（熵/二次），这些神经网络对大规模任务的表达不足。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，根据名人面对数据集，我们构建了Ave，Celeba！可通过使用生成模型（例如FID）的标准指标来定量评估Barycenter算法的数据集。
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.
