Supervised learning of sheared distributions using linearized optimal transport

DOI10.1007/s43670-022-00038-2zbMath1501.60010arXiv2201.10590OpenAlexW4306795876MaRDI QIDQ2098305

Caroline Moosmüller, Varun Khurana, Harish Kannan, Alexander Cloninger

Publication date: 17 November 2022

Published in: Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.10590

zbMATH Keywords

classificationlinearizationsupervised learningembeddingsoptimal transport

Mathematics Subject Classification ID

Probability measures on topological spaces (60B05) Geometric probability and stochastic geometry (60D05) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Optimal transportation (49Q22)

Related Items (2)

Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning ⋮ Applications of No-Collision Transportation Maps in Manifold Learning

Uses Software

• ElemStatLearn
• MNIST
• EMD
• Wasserstein GAN

Cites Work

• Unnamed Item
• Unnamed Item
• Wasserstein geometry of Gaussian measures
• The cumulative distribution transform and linear pattern classification
• The earth mover's distance as a metric for image retrieval
• A linear optimal transportation framework for quantifying and visualizing variations in sets of images
• Partitioning signal classes using transport transforms for data analysis and machine learning
• Convergence rates for discretized Monge-Ampère equations and quantitative stability of optimal transport
• People mover's distance: class level geometry using fast pairwise data adaptive transportation costs
• On Hölder continuity-in-time of the optimal transport map towards measures along a curve
• Hypothesis Testing with Efficient Method of Moments Estimation
• Polar factorization and monotone rearrangement of vector‐valued functions
• Kernel Mean Embedding of Distributions: A Review and Beyond
• The Radon Cumulative Distribution Transform and Its Application to Image Classification
• High-Dimensional Probability
• Two-sample statistics based on anisotropic kernels
• An Invitation to Statistics in Wasserstein Space
• Optimal Transport
• Polar factorization of maps on Riemannian manifolds

This page was built for publication: Supervised learning of sheared distributions using linearized optimal transport