Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning

DOI10.1137/22m1490053arXiv2204.06645OpenAlexW4379647309MaRDI QIDQ6171687

Nick Henscheid, Keaton Hamm, Unnamed Author

Publication date: 14 August 2023

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

Full work available at URL: https://arxiv.org/abs/2204.06645

zbMATH Keywords

optimal transportmanifold learningWasserstein spacenonlinear dimensionality reductionisomap

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Optimal transportation (49Q22)

Related Items

Applications of No-Collision Transportation Maps in Manifold Learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Computational Optimal Transport: With Applications to Data Science
• A sparse multiscale algorithm for dense optimal transport
• Nonlinear manifold representations for functional data
• Iterative scheme for solving optimal transportation problems arising in reflector design
• The geometry of optimal transportation
• The cumulative distribution transform and linear pattern classification
• Nonlinear manifold learning for early warnings in financial markets
• A linear optimal transportation framework for quantifying and visualizing variations in sets of images
• Manifold learning with arbitrary norms
• Domain decomposition for entropy regularized optimal transport
• Partitioning signal classes using transport transforms for data analysis and machine learning
• Supervised learning of sheared distributions using linearized optimal transport
• Wasserstein proximal of GANs
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Fast low-rank modifications of the thin singular value decomposition
• Multiscale geometric methods for data sets. I: Multiscale SVD, noise and curvature.
• Diffusion maps
• On the geometry of metric measure spaces. I
• Image manifolds which are isometric to Euclidean space
• Manifold parametrizations by eigenfunctions of the Laplacian and heat kernels
• Reducing the Dimensionality of Data with Neural Networks
• Polar factorization and monotone rearrangement of vector‐valued functions
• The Radon Cumulative Distribution Transform and Its Application to Image Classification
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems
• Nonlinear Dimensionality Reduction
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• Testing the manifold hypothesis
• Linear optimal transport embedding: provable Wasserstein classification for certain rigid transformations and perturbations
• Optimal Transport