Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning
From MaRDI portal
Publication:4686929
DOI10.1137/17M1140431zbMath1437.94027arXiv1708.01955OpenAlexW3102246635MaRDI QIDQ4686929
Matthieu Heitz, David Coeurjolly, Gabriel Peyré, Morgan A. Schmitz, Nicolas Bonneel, Fred Ngolè, Marco Cuturi, Jean-Luc Starck
Publication date: 10 October 2018
Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1708.01955
Special problems of linear programming (transportation, multi-index, data envelopment analysis, etc.) (90C08) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Numerical methods in optimal control (49M99)
Related Items
Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees, A general drift estimation procedure for stochastic differential equations with additive fractional noise, Estimation of Wasserstein distances in the spiked transport model, A family of pairwise multi-marginal optimal transports that define a generalized metric, Unnamed Item, Wasserstein model reduction approach for parametrized flow problems in porous media, Learning to generate Wasserstein barycenters, Asymptotics for Strassen's optimal transport problem, A column generation approach to the discrete barycenter problem, Semi-discrete optimal transport: a solution procedure for the unsquared Euclidean distance case, Metrics and barycenters for point pattern data, Unnamed Item, Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning, Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications, Ground metric learning on graphs, Minimax estimation of smooth optimal transport maps, Wasserstein index generation model: automatic generation of time-series index with application to economic policy uncertainty, Multigrid methods for image registration model based on optimal mass transport, Kantorovich-Rubinstein distance and barycenter for finitely supported measures: foundations and algorithms, Shared Prior Learning of Energy-Based Models for Image Reconstruction, Empirical Regularized Optimal Transport: Statistical Theory and Applications, Rethinking data-driven point spread function modeling with a differentiable optical model
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A survey of the Schrödinger problem and some of its connections with optimal transport
- Geodesic PCA in the Wasserstein space by convex PCA
- A class of Cartesian grid embedded boundary algorithms for incompressible flow with time-varying complex geometries
- On the scaling of multidimensional matrices
- The auction algorithm: A distributed relaxation method for the assignment problem
- A convexity principle for interacting gases
- Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
- Introductory lectures on convex optimization. A basic course.
- The earth mover's distance as a metric for image retrieval
- Transportation cost for Gaussian and other product measures
- A linear optimal transportation framework for quantifying and visualizing variations in sets of images
- Distribution's template estimate with Wasserstein metrics
- Sliced and Radon Wasserstein barycenters of measures
- On minimum Kantorovich distance estimators
- Optimal mass transport for registration and warping
- A Smoothed Dual Approach for Variational Wasserstein Problems
- Convolutional wasserstein distances
- Remark on “algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound constrained optimization”
- Reducing the Dimensionality of Data with Neural Networks
- Point Spread Function Field Learning Based on Optimal Transport Distances
- Barycenters in the Wasserstein Space
- Numerical methods for matching for teams and Wasserstein barycenters
- Evaluating Derivatives
- Online Dictionary Learning for Kernel LMS
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
- Fast Discrete Distribution Clustering Using Wasserstein Barycenter With Sparse Support
- Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning
- Iterative Bregman Projections for Regularized Transportation Problems
- Learning the parts of objects by non-negative matrix factorization
- Design of Non-Linear Kernel Dictionaries for Object Recognition
- Asymptotic Properties and Robustness of Minimum Dissimilarity Estimators of Location-scale Parameters
- Some methods of speeding up the convergence of iteration methods
- Diagonal Equivalence to Matrices with Prescribed Row and Column Sums
- A Direct Formulation for Sparse PCA Using Semidefinite Programming
- On a Least Squares Adjustment of a Sampled Frequency Table When the Expected Marginal Totals are Known
- Heavy-ball method in nonconvex optimization problems
