Papers › On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient...

On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods

21 Dec 2023arXiv:2312.13970archive 2025-07-28

Anh Duc Nguyen, Tuan Dung Nguyen, Quang Minh Nguyen, Hoang H. Nguyen, Lam M. Nguyen, Kim-Chuan Toh

This paper studies the Partial Optimal Transport (POT) problem between two unbalanced measures with at most n supports and its applications in various AI tasks such as color transfer or domain adaptation. There is hence the need for fast approximations of POT with increasingly large problem sizes in arising applications. We first theoretically and experimentally investigate the infeasibility of the state-of-the-art Sinkhorn algorithm for POT due to its incompatible rounding procedure, which consequently degrades its qualitative performance in real world applications like point-cloud registration. To this end, we propose a novel rounding algorithm for POT, and then provide a feasible Sinkhorn procedure with a revised computation complexity of 𝒪(n²/ε⁴). Our rounding algorithm also permits the development of two first-order methods to approximate the POT problem. The first algorithm, Adaptive Primal-Dual Accelerated Gradient Descent (APDAGD), finds an ε-approximate solution to the POT problem in 𝒪(n^(2.5)/ε), which is better in ε than revised Sinkhorn. The second method, Dual Extrapolation, achieves the computation complexity of 𝒪(n²/ε), thereby being the best in the literature. We further demonstrate the flexibility of POT compared to standard OT as well as the practicality of our algorithms on real applications where two marginal distributions are unbalanced.

PaperPDFCode

Code

joshnguyen99/partialot officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationPoint Cloud Registration

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections