Gromov-Wasserstein Distance based Object Matching: Asymptotic Inference
2020-06-22 | Preprint
Spring zu: Zitieren & Links | Dokumente & Medien | Details | Versionsgeschichte
Dokumente & Medien
Details
- Autor(en)
- Weitkamp, Christoph Alexander; Proksch, Katharina; Tameling, Carla; Munk, Axel
- Zusammenfassung
- In this paper, we aim to provide a statistical theory for object matching based on the Gromov-Wasserstein distance. To this end, we model general objects as metric measure spaces. Based on this, we propose a simple and efficiently computable asymptotic statistical test for pose invariant object discrimination. This is based on an empirical version of a $\betaehBtrimmed lower bound of the Gromov-Wasserstein distance. We derive for $\beta\in[0,1/2)$ distributional limits of this test statistic. To this end, we introduce a novel ehBtype process indexed in $\beta$ and show its weak convergence. Finally, the theory developed is investigated in Monte Carlo simulations and applied to structural protein comparisons.
- Erscheinungsdatum
- 22-Juni-2020
- Project
- EXC 2067: Multiscale Bioimaging
- Arbeitsgruppe
- RG Munk