A Sparse Multiscale Algorithm for Dense Optimal Transport
TLDR
This work provides a framework to verify global optimality of a discrete transport plan locally and explicitly describes how to select the sparse sub-problems for several cost functions, including the noisy squared Euclidean distance.Abstract:
Discrete optimal transport solvers do not scale well on dense large problems since they do not explicitly exploit the geometric structure of the cost function. In analogy to continuous optimal transport, we provide a framework to verify global optimality of a discrete transport plan locally. This allows the construction of an algorithm to solve large dense problems by considering a sequence of sparse problems instead. The algorithm lends itself to being combined with a hierarchical multiscale scheme. Any existing discrete solver can be used as internal black-box. We explicitly describe how to select the sparse sub-problems for several cost functions, including the noisy squared Euclidean distance. Significant reductions in run-time and memory requirements have been observed.read more
Citations
More filters
Posted Content
Computational Optimal Transport
Gabriel Peyré,Marco Cuturi +1 more
TL;DR: This short book reviews OT with a bias toward numerical methods and their applications in data sciences, and sheds lights on the theoretical properties of OT that make it particularly useful for some of these applications.
Journal ArticleDOI
Optimal Mass Transport: Signal processing and machine-learning applications
TL;DR: A practical overview of the mathematical underpinnings of mass transport-related methods, including numerical implementation, are provided as well as a review, with demonstrations, of several applications.
Journal ArticleDOI
Scaling algorithms for unbalanced optimal transport problems
Journal ArticleDOI
Application of optimal transport and the quadratic Wasserstein metric to full-waveform inversion
TL;DR: In this paper, the quadratic Wasserstein metric is used to measure amplitude differences and global phase shifts, which helps to avoid cycle-skipping issues in full waveform inversion.
Posted Content
Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning
TL;DR: This tutorial argues that Wasserstein distributionally robust optimization has interesting ramifications for statistical learning and motivates new approaches for fundamental learning tasks such as classification, regression, maximum likelihood estimation or minimum mean square error estimation, among others.
References
More filters
Journal ArticleDOI
The Hungarian method for the assignment problem
TL;DR: This paper has always been one of my favorite children, combining as it does elements of the duality of linear programming and combinatorial tools from graph theory, and it may be of some interest to tell the story of its origin this article.
Book
Network Flows: Theory, Algorithms, and Applications
TL;DR: In-depth, self-contained treatments of shortest path, maximum flow, and minimum cost flow problems, including descriptions of polynomial-time algorithms for these core models are presented.
Book
Optimal Transport: Old and New
TL;DR: In this paper, the authors provide a detailed description of the basic properties of optimal transport, including cyclical monotonicity and Kantorovich duality, and three examples of coupling techniques.
Journal ArticleDOI
The Earth Mover's Distance as a Metric for Image Retrieval
TL;DR: This paper investigates the properties of a metric between two distributions, the Earth Mover's Distance (EMD), for content-based image retrieval, and compares the retrieval performance of the EMD with that of other distances.
Book
Convex Analysis and Monotone Operator Theory in Hilbert Spaces
TL;DR: This book provides a largely self-contained account of the main results of convex analysis and optimization in Hilbert space, and a concise exposition of related constructive fixed point theory that allows for a wide range of algorithms to construct solutions to problems in optimization, equilibrium theory, monotone inclusions, variational inequalities, and convex feasibility.