Fast Gradient Computation for Gromov-Wasserstein Distance

arXiv:2404.08970v1 Announce Type: new
Abstract: The Gromov-Wasserstein distance is a notable extension of optimal transport. In contrast to the classic Wasserstein distance, it solves a quadratic assignment problem that minimizes the pair-wise distance distortion under the transportation of distributions and thus could apply to distributions in different spaces. These properties make Gromov-Wasserstein widely applicable to many fields, such as computer graphics and machine learning. However, the computation of the Gromov-Wasserstein distance and transport plan is expensive. The well-known Entropic Gromov-Wasserstein …

abstract apply arxiv computation contrast cs.lg extension gradient spaces transport transportation type wise