SK converges linearly at rate 1-σ2 once near the optimum, with explicit burn-in, and can be accelerated by gradient methods on the semi-dual.
A geometric structure of acceleration and its role in making gradients small fast.Advances in Neural Information Processing Systems, 34:11999–12012, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tight Nonasymptotic Local Convergence of Sinkhorn-Knopp
SK converges linearly at rate 1-σ2 once near the optimum, with explicit burn-in, and can be accelerated by gradient methods on the semi-dual.