Supervised optimal transport
From MaRDI portal
Publication:5048639
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 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.
Recommendations
Cites work
- scientific article; zbMATH DE number 3001084 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 3099866 (Why is no real title available?)
- A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
- A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
- A parallel method for earth mover's distance
- Asymptotic analysis of the exponential penalty trajectory in linear programming
- Combinatorial matrix classes
- Computations of optimal transport distance with Fisher information regularization
- Concerning nonnegative matrices and doubly stochastic matrices
- Diagonal Equivalence to Matrices with Prescribed Row and Column Sums
- Diffeomorphic density matching by optimal information transport
- Entropic approximation of Wasserstein gradient flows
- Generalized Sinkhorn iterations for regularizing inverse problems using optimal mass transport
- Generalized unnormalized optimal transport and its fast algorithms
- Iterative Bregman projections for regularized transportation problems
- On the scaling of multidimensional matrices
- Polar factorization and monotone rearrangement of vector‐valued functions
- Regularized discrete optimal transport
- Scaling algorithms for unbalanced optimal transport problems
- Unbalanced optimal transport: dynamic and Kantorovich formulations
- Unnormalized optimal transport
Cited in
(6)- Mirror variational transport: a particle-based algorithm for distributional optimization on constrained domains
- Supervised learning of sheared distributions using linearized optimal transport
- Optimal transport driven CycleGAN for unsupervised learning in inverse problems
- The directional optimal transport
- Data-driven optimal transport
- Non-convex relaxation of optimal transport for color transfer between images
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)