arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2112.02424cs.LG
收藏

变分Wasserstein梯度流

Variational Wasserstein gradient flow

Georgia Institute of Technology(佐治亚理工学院);University of Washington, Seattle(华盛顿大学西雅图分校)

Jiaojiao Fan, Qinsheng Zhang, Amirhossein Taghvaei, Yongxin Chen

摘要:

Wasserstein梯度流已经成为解决概率分布空间上的优化问题的一种有前途的方法。最近的趋势是使用众所周知的JKO计划与输入凸神经网络的组合,以数字方式实现近端步骤。在这种设置中,最具挑战性的步骤是根据样本来评估明确涉及密度的函数,例如熵。本文建立在最近的作品有轻微的,但至关重要的区别:我们建议利用变分制定的目标函数制定为最大化的参数类的功能。从理论上讲,建议的变分公式允许直接为经验分布构建梯度流,并具有定义明确且有意义的目标函数。在计算上,这种方法取代了现有方法中计算成本高的步骤,以处理涉及密度的目标函数,内部循环更新只需要一小批样本,并且可以很好地随维度扩展。所提出的方法的性能和可扩展性说明了几个数值实验的帮助下,涉及高维合成和真实数据集。

英文摘要:

Wasserstein gradient flow has emerged as a promising approach to solve optimization problems over the space of probability distributions. A recent trend is to use the well-known JKO scheme in combination with input convex neural networks to numerically implement the proximal step. The most challenging step, in this setup, is to evaluate functions involving density explicitly, such as entropy, in terms of samples. This paper builds on the recent works with a slight but crucial difference: we propose to utilize a variational formulation of the objective function formulated as maximization over a parametric class of functions. Theoretically, the proposed variational formulation allows the construction of gradient flows directly for empirical distributions with a well-defined and meaningful objective function. Computationally, this approach replaces the computationally expensive step in existing methods, to handle objective functions involving density, with inner loop updates that only require a small batch of samples and scale well with the dimension. The performance and scalability of the proposed method are illustrated with the aid of several numerical experiments involving high-dimensional synthetic and real datasets.

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。

↑