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 2602.22003cs.LGmath.OCstat.ML
收藏

基于神经网络的Wasserstein地轴与最优传输动力学求解器

Neural solver for Wasserstein Geodesics and optimal transport dynamics

Hailiang Liu, Yan-Han Chen

AI总结:

本文提出了一种基于神经网络的求解器,用于计算Wasserstein地轴和最优传输动力学,通过近似相关函数实现对目标分布的直接采样。

摘要:

近年来,机器学习社区越来越多地采用最优传输(OT)框架来建模分布关系。在本工作中,我们引入了一种基于样本的神经求解器,用于计算源分布与目标分布之间的Wasserstein地轴,以及相关的速度场。基于最优传输问题的动力学表述,我们将约束优化问题重新表述为一个极小极大问题,利用深度神经网络来近似相关函数。这种方法不仅提供了Wasserstein地轴,还恢复了OT映射,从而能够直接从目标分布进行采样。通过估计OT映射,我们获得了粒子轨迹上的速度估计,从而可以学习完整的速度场。该框架具有灵活性,可以轻松扩展到一般成本函数,包括常用的二次成本。我们通过在合成和真实数据集上的实验展示了该方法的有效性。

英文摘要:

In recent years, the machine learning community has increasingly embraced the optimal transport (OT) framework for modeling distributional relationships. In this work, we introduce a sample-based neural solver for computing the Wasserstein geodesic between a source and target distribution, along with the associated velocity field. Building on the dynamical formulation of the optimal transport (OT) problem, we recast the constrained optimization as a minimax problem, using deep neural networks to approximate the relevant functions. This approach not only provides the Wasserstein geodesic but also recovers the OT map, enabling direct sampling from the target distribution. By estimating the OT map, we obtain velocity estimates along particle trajectories, which in turn allow us to learn the full velocity field. The framework is flexible and readily extends to general cost functions, including the commonly used quadratic cost. We demonstrate the effectiveness of our method through experiments on both 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。

↑