Sinkhorn iterations converge to a Wasserstein mirror gradient flow (the Sinkhorn flow) as regularization epsilon goes to zero with iterations scaled as 1/epsilon.
[RW23] Cale Rankin and Leonard Wong, Bregman-Wasserstein divergence: geometry and applications , Math arxiv preprint arXiv:2302.05833
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.PR 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Wasserstein Mirror Gradient Flow as the limit of the Sinkhorn Algorithm
Sinkhorn iterations converge to a Wasserstein mirror gradient flow (the Sinkhorn flow) as regularization epsilon goes to zero with iterations scaled as 1/epsilon.