学习非规范化模型的Wasserstein最小速度方法
A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models
摘要：
分数匹配为学习灵活的非规范化模型提供了一种有效的方法，但其可扩展性受到评估二阶导数的需求的限制。在本文中，我们提出了一个可扩展的近似一般家庭的学习目标，包括分数匹配，通过观察这些目标和Wasserstein梯度流之间的新的连接。我们目前的应用程序与承诺学习神经密度估计流形上，训练隐式变分和Wasserstein自动编码器与流形值的先验。
英文摘要：
Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family of learning objectives including score matching, by observing a new connection between these objectives and Wasserstein gradient flows. We present applications with promise in learning neural density estimators on manifolds, and training implicit variational and Wasserstein auto-encoders with a manifold-valued prior.
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。
