Sparse Regularized Optimal Transport with Deformed q-Entropy

4Citations
Citations of this article
11Readers
Mendeley users who have this article in their library.

Abstract

Optimal transport is a mathematical tool that has been a widely used to measure the distance between two probability distributions. To mitigate the cubic computational complexity of the vanilla formulation of the optimal transport problem, regularized optimal transport has received attention in recent years, which is a convex program to minimize the linear transport cost with an added convex regularizer. Sinkhorn optimal transport is the most prominent one regularized with negative Shannon entropy, leading to densely supported solutions, which are often undesirable in light of the interpretability of transport plans. In this paper, we report that a deformed entropy designed by q-algebra, a popular generalization of the standard algebra studied in Tsallis statistical mechanics, makes optimal transport solutions supported sparsely. This entropy with a deformation parameter q interpolates the negative Shannon entropy ( (Formula presented.) ) and the squared 2-norm ( (Formula presented.) ), and the solution becomes more sparse as q tends to zero. Our theoretical analysis reveals that a larger q leads to a faster convergence when optimized with the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm. In summary, the deformation induces a trade-off between the sparsity and convergence speed.

References Powered by Scopus

This article is free to access.

8008Citations
837Readers
Get full text
Get full text

Cited by Powered by Scopus

Safe Screening for l<inf>2</inf>-penalized Unbalanced Optimal Transport Problem

2Citations
1Readers
Get full text

Accelerating Unbalanced Optimal Transport Problem Using Dynamic Penalty Updating

1Citations
1Readers
Get full text

Sparse Domain Transfer via Elastic Net Regularization

0Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Bao, H., & Sakaue, S. (2022). Sparse Regularized Optimal Transport with Deformed q-Entropy. Entropy, 24(11). https://doi.org/10.3390/e24111634

Readers over time

‘22‘23‘2402468

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 2

50%

Researcher 2

50%

Readers' Discipline

Tooltip

Computer Science 1

25%

Physics and Astronomy 1

25%

Psychology 1

25%

Economics, Econometrics and Finance 1

25%

Save time finding and organizing research with Mendeley

Sign up for free
0