Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.14673 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908328796356608 |
|---|---|
| author | Tran, Hoang Anh Nguyen, Binh Tuan Soh, Yong Sheng |
| author_facet | Tran, Hoang Anh Nguyen, Binh Tuan Soh, Yong Sheng |
| contents | The Gromov-Wasserstein (GW) problem is an extension of the classical optimal transport problem to settings where the source and target distributions reside in incomparable spaces, and for which a cost function that attributes the price of moving resources is not available. The sum-of-squares (SOS) hierarchy is a principled method for deriving tractable semidefinite relaxations to generic polynomial optimization problems. In this work, we apply ideas from the moment-SOS hierarchy to solve the GW problem.
More precisely, we identify extensions of the moment-SOS hierarchy, previously introduced for the discretized GW problem, such that they remain valid for general probability distributions. This process requires a suitable generalization of positive semidefiniteness over finite-dimensional vector spaces to the space of probability distributions. We prove the following properties concerning these continuous extensions: First, these relaxations form a genuine hierarchy in that the optimal value converges to the GW distance. Second, each of these relaxations induces a pseudo-metric over the collection of metric measure spaces. Crucially, unlike the GW problem, these induced instances are tractable to compute -- the discrete analogs are expressible as semidefinite programs and hence are tractable to solve. Separately from these properties, we also establish a statistical consistency result arising from sampling the source and target distributions. Our work suggests fascinating applications of the SOS hierarchy to optimization problems over probability distributions in settings where the objective and constraint depend on these distributions in a polynomial way. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14673 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Moment Sum-of-Squares Hierarchy for Gromov Wasserstein: Continuous Extensions and Sample Complexity Tran, Hoang Anh Nguyen, Binh Tuan Soh, Yong Sheng Optimization and Control The Gromov-Wasserstein (GW) problem is an extension of the classical optimal transport problem to settings where the source and target distributions reside in incomparable spaces, and for which a cost function that attributes the price of moving resources is not available. The sum-of-squares (SOS) hierarchy is a principled method for deriving tractable semidefinite relaxations to generic polynomial optimization problems. In this work, we apply ideas from the moment-SOS hierarchy to solve the GW problem. More precisely, we identify extensions of the moment-SOS hierarchy, previously introduced for the discretized GW problem, such that they remain valid for general probability distributions. This process requires a suitable generalization of positive semidefiniteness over finite-dimensional vector spaces to the space of probability distributions. We prove the following properties concerning these continuous extensions: First, these relaxations form a genuine hierarchy in that the optimal value converges to the GW distance. Second, each of these relaxations induces a pseudo-metric over the collection of metric measure spaces. Crucially, unlike the GW problem, these induced instances are tractable to compute -- the discrete analogs are expressible as semidefinite programs and hence are tractable to solve. Separately from these properties, we also establish a statistical consistency result arising from sampling the source and target distributions. Our work suggests fascinating applications of the SOS hierarchy to optimization problems over probability distributions in settings where the objective and constraint depend on these distributions in a polynomial way. |
| title | Moment Sum-of-Squares Hierarchy for Gromov Wasserstein: Continuous Extensions and Sample Complexity |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2504.14673 |