Applications of No-Collision Transportation Maps in Manifold Learning

DOI10.1137/23M1567771arXiv2304.00199OpenAlexW4392018280MaRDI QIDQ6202282FDOQ6202282

Elisa Negrini, Levon Nurbekyan

Publication date: 26 March 2024

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Abstract: In this work, we investigate applications of no-collision transportation maps introduced in [Nurbekyan et. al., 2020] in manifold learning for image data. Recently, there has been a surge in applying transportation-based distances and features for data representing motion-like or deformation-like phenomena. Indeed, comparing intensities at fixed locations often does not reveal the data structure. No-collision maps and distances developed in [Nurbekyan et. al., 2020] are sensitive to geometric features similar to optimal transportation (OT) maps but much cheaper to compute due to the absence of optimization. In this work, we prove that no-collision distances provide an isometry between translations (respectively dilations) of a single probability measure and the translation (respectively dilation) vectors equipped with a Euclidean distance. Furthermore, we prove that no-collision transportation maps, as well as OT and linearized OT maps, do not in general provide an isometry for rotations. The numerical experiments confirm our theoretical findings and show that no-collision distances achieve similar or better performance on several manifold learning tasks compared to other OT and Euclidean-based methods at a fraction of a computational cost.

Full work available at URL: https://arxiv.org/abs/2304.00199

zbMATH Keywords

manifold learningnonlinear dimensionality reductionoptimal transportationno-collision transportation maps

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09)

Cites Work

• Title not available (Why is that?)
• Diffusion maps
• Modern multidimensional scaling. Theory and applications.
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Polar factorization and monotone rearrangement of vector‐valued functions
• Optimal Transport
• On optimal matchings
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Gradient flows with metric and differentiable structures, and applications to the Wasserstein space
• Manifold parametrizations by eigenfunctions of the Laplacian and heat kernels
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
• Polar factorization of maps on Riemannian manifolds
• On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces
• Sliced and Radon Wasserstein barycenters of measures
• Nonlinear Dimensionality Reduction
• A linear optimal transportation framework for quantifying and visualizing variations in sets of images
• A sparse multiscale algorithm for dense optimal transport
• The Radon Cumulative Distribution Transform and Its Application to Image Classification
• Testing the manifold hypothesis
• The cumulative distribution transform and linear pattern classification
• Manifold learning with arbitrary norms
• Domain decomposition for entropy regularized optimal transport
• Supervised learning of sheared distributions using linearized optimal transport
• No-collision transportation maps
• Linear optimal transport embedding: provable Wasserstein classification for certain rigid transformations and perturbations
• Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning

Cited In (1)

• On Wasserstein distances for affine transformations of random vectors

This page was built for publication: Applications of No-Collision Transportation Maps in Manifold Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6202282)