SK converges in O(log n - log ε) iterations for well-bounded EOT independent of η||C||_∞, O(log(1/ε)) with pre-scaling; general scaling has a sharp density phase transition for ν-independence.
Improved complexity analysis of the sinkhorn and greenkhorn algorithms for optimal transport.arXiv preprint arXiv:2305.14939
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Derives the cold Sinkhorn limiting dynamics as tau approaches zero, proving finite-time convergence to unregularized OT and improved O(tau^{-1}) iteration complexity for dual suboptimality.
Proves sharp O(1/k) rate for Sinkhorn via local bipartite graph analysis of positive-mass edges, bootstrapped from prior almost-sharp global bound.
citing papers explorer
-
On the Efficiency of Sinkhorn-Knopp for Entropically Regularized Optimal Transport
SK converges in O(log n - log ε) iterations for well-bounded EOT independent of η||C||_∞, O(log(1/ε)) with pre-scaling; general scaling has a sharp density phase transition for ν-independence.
-
Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization
Derives the cold Sinkhorn limiting dynamics as tau approaches zero, proving finite-time convergence to unregularized OT and improved O(tau^{-1}) iteration complexity for dual suboptimality.
-
Sharp $O(1/k)$ convergence rate for the Sinkhorn algorithm via a local analysis
Proves sharp O(1/k) rate for Sinkhorn via local bipartite graph analysis of positive-mass edges, bootstrapped from prior almost-sharp global bound.