Partial Optimal Transport (POT) addresses the problem of transporting only a fraction of the total mass between two distributions, making it suitable when marginals have unequal size or contain outliers. While Sinkhorn-based methods are widely used, their complexity bounds for POT remain suboptimal and can limit scalability. We introduce Accelerated Sinkhorn for POT (ASPOT), which integrates alternating minimization with Nesterov-style acceleration in the POT setting, yielding a complexity of O(n7/3ε−5/3). We also show that an informed choice of the entropic parameter γ improves rates for the classical Sinkhorn method. Experiments on real-world applications validate our theories and demonstrate the favorable performance of our proposed methods.
@article{arxiv.2601.17196,
title = {Accelerated Sinkhorn Algorithms for Partial Optimal Transport},
author = {Nghia Thu Truong and Qui Phu Pham and Quang Nguyen and Dung Luong and Mai Tran},
journal= {arXiv preprint arXiv:2601.17196},
year = {2026}
}