Stability of Schr"odinger Potentials and Convergence of Sinkhorn's Algorithm
Not on the map. Why?
Abstract (arXiv)
We study the stability of entropically regularized optimal transport with respect to the marginals. Given marginals converging weakly, we establish a strong convergence for the Schr"odinger potentials describing the density of the optimal couplings. When the marginals converge in total variation, the optimal couplings also converge in total variation. This is applied to show that Sinkhorn's algorithm converges in total variation when costs are quadratic and marginals are subgaussian, or more generally for all continuous costs satisfying an integrability condition.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jan 2022.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 4; 2023: 4; 2024: 1; 2025: 1; 2026: 3.
13 papers.
Sort:
By area:
- 2022Riemannian Score-Based Generative Modellingcited by 216
- 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputationcited by 26
- 2022An improved central limit theorem and fast convergence rates for entropic transportation costscited by 18
- 2024Reflected Schr"odinger Bridge for Constrained Generative Modelingcited by 12
- 2022Convergence Rates for Regularized Optimal Transport via Quantizationcited by 11
- 2022Riemannian Diffusion Schr"odinger Bridgecited by 10
- 2023Wasserstein Mirror Gradient Flow as the limit of the Sinkhorn Algorithmcited by 10
- 2023Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithmcited by 8
- 2023Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approachcited by 7
- 2025Variational Online Mirror Descent for Robust Learning in Schr"odinger Bridgecited by 2
- 2026On the Expressive Power of Transformers for Contextual Relationscited by 1
- 2026Uniform Statistical Convergence of Empirical Sinkhorn Potentials with Exponential and Polynomial Dependence on the Regularization Parametercited by 0
1 more
- 2026Low-Budget Active Learning through Entropic Optimal Transport1 Oct 2026
- 2026Uniform Statistical Convergence of Empirical Sinkhorn Potentials with Exponential and Polynomial Dependence on the Regularization Parameter29 Aug 2026
- 2026On the Expressive Power of Transformers for Contextual Relations26 Mar 2026
- 2025Variational Online Mirror Descent for Robust Learning in Schr"odinger Bridge3 Apr 2025
- 2024Reflected Schr"odinger Bridge for Constrained Generative Modeling6 Jan 2024
- 2023Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm7 Nov 2023
- 2023Wasserstein Mirror Gradient Flow as the limit of the Sinkhorn Algorithm31 Jul 2023
- 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputation12 May 2023
- 2023Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach13 Apr 2023
- 2022Convergence Rates for Regularized Optimal Transport via Quantization30 Aug 2022
- 2022Riemannian Diffusion Schr"odinger Bridge7 Jul 2022
- 2022An improved central limit theorem and fast convergence rates for entropic transportation costs19 Apr 2022
1 more
- 2022Riemannian Score-Based Generative Modelling6 Feb 2022
- 2022Riemannian Score-Based Generative Modellingcited by 216
- 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputationcited by 26
- 2024Reflected Schr"odinger Bridge for Constrained Generative Modelingcited by 12
- 2022Riemannian Diffusion Schr"odinger Bridgecited by 10
- 2024Reflected Schr"odinger Bridge for Constrained Generative Modeling6 Jan 2024
- 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputation12 May 2023
- 2022Riemannian Diffusion Schr"odinger Bridge7 Jul 2022
- 2022Riemannian Score-Based Generative Modelling6 Feb 2022
- 2022An improved central limit theorem and fast convergence rates for entropic transportation costscited by 18
- 2022Convergence Rates for Regularized Optimal Transport via Quantizationcited by 11
- 2023Wasserstein Mirror Gradient Flow as the limit of the Sinkhorn Algorithmcited by 10
- 2023Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithmcited by 8
- 2023Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approachcited by 7
- 2025Variational Online Mirror Descent for Robust Learning in Schr"odinger Bridgecited by 2
- 2026On the Expressive Power of Transformers for Contextual Relationscited by 1
- 2026Uniform Statistical Convergence of Empirical Sinkhorn Potentials with Exponential and Polynomial Dependence on the Regularization Parametercited by 0
- 2026Low-Budget Active Learning through Entropic Optimal Transportcited by 0
- 2026Low-Budget Active Learning through Entropic Optimal Transport1 Oct 2026
- 2026Uniform Statistical Convergence of Empirical Sinkhorn Potentials with Exponential and Polynomial Dependence on the Regularization Parameter29 Aug 2026
- 2026On the Expressive Power of Transformers for Contextual Relations26 Mar 2026
- 2025Variational Online Mirror Descent for Robust Learning in Schr"odinger Bridge3 Apr 2025
- 2023Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm7 Nov 2023
- 2023Wasserstein Mirror Gradient Flow as the limit of the Sinkhorn Algorithm31 Jul 2023
- 2023Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach13 Apr 2023
- 2022Convergence Rates for Regularized Optimal Transport via Quantization30 Aug 2022
- 2022An improved central limit theorem and fast convergence rates for entropic transportation costs19 Apr 2022