arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.14957cs.LG
收藏

强同构神经最优传输跨不可比空间

Strongly Isomorphic Neural Optimal Transport Across Incomparable Spaces

Harvard University(哈佛大学);Microsoft Research(微软研究院)

Athina Sotiropoulou, David Alvarez-Melis

AI总结:

本文提出一种基于强同构不变性的Gromov-Monge神经最优传输方法,通过分解映射为近似同构和GM最优两部分,简化架构并保证理论性能,适用于跨不可比空间的学习。

摘要:

最优传输(OT)最近已成为学习分布间最小位移映射的强大框架。主流方法涉及对OT的Monge公式进行神经参数化,通常假设两个分布位于同一空间。然而,跨“不可比空间”(例如不同维度)的设置,对应于Gromov-Wasserstein距离,仍未被充分探索,现有方法往往对代价函数施加限制性假设。在本文中,我们提出了一种新的Gromov-Monge(GM)问题的神经公式,该公式植根于其基本性质之一:对强同构的不变性。我们通过将可学习的OT映射分解为两个部分来实现这一性质:(i)源分布与中间参考分布之间的近似强同构,以及(ii)该参考与目标分布之间的GM最优映射。我们的公式利用并扩展了Uscidda & Cuturi(2023)的Monge间隙正则化器,以消除其他神经OT方法对复杂架构的需求,产生了一种简单但实用的方法,并享有有利的理论保证。我们的初步实验结果表明,我们的框架为学习跨不同空间的OT映射提供了一种有前景的方法。

英文摘要:

Optimal Transport (OT) has recently emerged as a powerful framework for learning minimal-displacement maps between distributions. The predominant approach involves a neural parametrization of the Monge formulation of OT, typically assuming the same space for both distributions. However, the setting across ``incomparable spaces'' (e.g., of different dimensionality), corresponding to the Gromov- Wasserstein distance, remains underexplored, with existing methods often imposing restrictive assumptions on the cost function. In this paper, we present a novel neural formulation of the Gromov-Monge (GM) problem rooted in one of its fundamental properties: invariance to strong isomorphisms. We operationalize this property by decomposing the learnable OT map into two components: (i) an approximate strong isomorphism between the source distribution and an intermediate reference distribution, and (ii) a GM-optimal map between this reference and the target distribution. Our formulation leverages and extends the Monge gap regularizer of Uscidda & Cuturi (2023) to eliminate the need for complex architectural requirements of other neural OT methods, yielding a simple but practical method that enjoys favorable theoretical guarantees. Our preliminary empirical results show that our framework provides a promising approach to learn OT maps across diverse spaces.

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。

↑