Supervised Optimal Transport

DOI10.1137/22M1469171zbMATH Open1501.49026arXiv2206.13410OpenAlexW4308021354MaRDI QIDQ5048639FDOQ5048639

Qing Nie, Yanxiang Zhao, Zixuan Cang

Publication date: 16 November 2022

Published in: SIAM Journal on Applied Mathematics (Search for Journal in Brave)

Abstract: Optimal Transport, a theory for optimal allocation of resources, is widely used in various fields such as astrophysics, machine learning, and imaging science. However, many applications impose elementwise constraints on the transport plan which traditional optimal transport cannot enforce. Here we introduce Supervised Optimal Transport (sOT) that formulates a constrained optimal transport problem where couplings between certain elements are prohibited according to specific applications. sOT is proved to be equivalent to an $l^1$ penalized optimization problem, from which efficient algorithms are designed to solve its entropy regularized formulation. We demonstrate the capability of sOT by comparing it to other variants and extensions of traditional OT in color transfer problem. We also study the barycenter problem in sOT formulation, where we discover and prove a unique reverse and portion selection (control) mechanism. Supervised optimal transport is broadly applicable to applications in which constrained transport plan is involved and the original unit should be preserved by avoiding normalization.

Full work available at URL: https://arxiv.org/abs/2206.13410

zbMATH Keywords

entropic regularizationDykstra algorithmconstrained transport planinfinity cost matrixsupervised optimal transportunnormalized marginal distributions

Mathematics Subject Classification ID

Optimal transportation (49Q22) Transportation, logistics and supply chain management (90B06)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Concerning nonnegative matrices and doubly stochastic matrices
• A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
• Scaling algorithms for unbalanced optimal transport problems
• Polar factorization and monotone rearrangement of vector‐valued functions
• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• Iterative Bregman Projections for Regularized Transportation Problems
• Regularized Discrete Optimal Transport
• On the scaling of multidimensional matrices
• Unbalanced optimal transport: dynamic and Kantorovich formulations
• Asymptotic analysis of the exponential penalty trajectory in linear programming
• A parallel method for earth mover's distance
• Entropic Approximation of Wasserstein Gradient Flows
• Diagonal Equivalence to Matrices with Prescribed Row and Column Sums
• Diffeomorphic Density Matching by Optimal Information Transport
• Unnormalized optimal transport
• Computations of optimal transport distance with Fisher information regularization
• Generalized Sinkhorn Iterations for Regularizing Inverse Problems Using Optimal Mass Transport
• Generalized unnormalized optimal transport and its fast algorithms

Cited In (1)

• Data-driven optimal transport

Uses Software

• Wasserstein GAN

This page was built for publication: Supervised Optimal Transport

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5048639)