Measure transfer via stochastic slicing and matching
From MaRDI portal
Publication:6443389
arXiv2307.05705MaRDI QIDQ6443389FDOQ6443389
Authors: Shiying Li, Caroline Moosmüller 
Publication date: 11 July 2023
Abstract: This paper studies iterative schemes for measure transfer and approximation problems, which are defined through a slicing-and-matching procedure. Similar to the sliced Wasserstein distance, these schemes benefit from the availability of closed-form solutions for the one-dimensional optimal transport problem and the associated computational advantages. While such schemes have already been successfully utilized in data science applications, not too many results on their convergence are available. The main contribution of this paper is an almost sure convergence proof for stochastic slicing-and-matching schemes. The proof builds on an interpretation as a stochastic gradient descent scheme on the Wasserstein space. Numerical examples on step-wise image morphing are demonstrated as well.
Has companion code repository: https://github.com/shiyinglive/slicematchingtransport
Learning and adaptive systems in artificial intelligence (68T05) Optimal transportation (49Q22) Geometric probability and stochastic geometry (60D05) Probabilistic models, generic numerical methods in probability and statistics (65C20)
This page was built for publication: Measure transfer via stochastic slicing and matching
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6443389)
