Geodesic PCA versus Log-PCA of Histograms in the Wasserstein Space

DOI10.1137/17M1143459zbMath1387.62077arXiv1708.08143OpenAlexW2795320988WikidataQ125801157 ScholiaQ125801157MaRDI QIDQ4610140

Elsa Cazelles, Nicolas Papadakis, Marco Cuturi, Vivien Seguy, Jérémie Bigot

Publication date: 5 April 2018

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1708.08143

zbMATH Keywords

nonconvex optimizationWasserstein spacegeodesic principal component analysis

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Convex programming (90C25) Numerical optimization and variational techniques (65K10)

Related Items

Statistical shape analysis of brain arterial networks (BAN), Semi-discrete optimal transport: hardness, regularization and numerical solution, Estimation of Wasserstein distances in the spiked transport model, Depth and outliers for samples of sets and random sets distributions, Wasserstein Regression, Independent Nonlinear Component Analysis, A Variational Model Dedicated to Joint Segmentation, Registration, and Atlas Generation for Shape Analysis, Machine learning and optimal transport: some statistical and algorithmic tools, Long-time principal geodesic analysis in director-based dynamics of hybrid mechanical systems, Quantitative stability of optimal transport maps under variations of the target measure, Wasserstein gradients for the temporal evolution of probability distributions, Unnamed Item, Fréchet change-point detection, Unnamed Item, Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications, Minimax estimation of smooth optimal transport maps, Nonlinear model reduction on metric spaces. Application to one-dimensional conservative PDEs in Wasserstein spaces

Uses Software

• iPiano
• MNIST

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the ergodic convergence rates of a first-order primal-dual algorithm
• Geodesic PCA in the Wasserstein space by convex PCA
• An inertial forward-backward algorithm for monotone inclusions
• Optimal entropy-transport problems and a new Hellinger-Kantorovich distance between positive measures
• An interpolating distance between optimal transport and Fisher-Rao metrics
• Unbalanced optimal transport: dynamic and Kantorovich formulations
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• A linear optimal transportation framework for quantifying and visualizing variations in sets of images
• Geodesic regression and the theory of least squares on Riemannian manifolds
• Gradient flows with metric and differentiable structures, and applications to the Wasserstein space
• iPiano: Inertial Proximal Algorithm for Nonconvex Optimization
• Barycenters in the Wasserstein Space
• Polar factorization and monotone rearrangement of vector‐valued functions
• Geometric Methods for Spectral Analysis
• Iterative Bregman Projections for Regularized Transportation Problems
• Functional data analysis for density functions by transformation to a Hilbert space