Nearly Tight Convergence Bounds for Semi-Discrete Entropic Optimal Transport

Abstract

We derive nearly tight and non-asymptotic convergence bounds for solutions of entropic semi-discrete optimal transport. These bounds quantify the stability of the dual solutions of the regularized problem (sometimes called Sinkhorn potentials) w.r.t. the regularization parameter, for which we ensure a better than Lipschitz dependence. Such facts may be a first step towards a mathematical justification of $\varepsilon$-scaling heuristics for the numerical resolution of regularized semi-discrete optimal transport. Our results also entail a non-asymptotic and tight expansion of the difference between the entropic and the unregularized costs.

Cite

Text

Delalande. "Nearly Tight Convergence Bounds for Semi-Discrete Entropic Optimal Transport." Artificial Intelligence and Statistics, 2022.

Markdown

[Delalande. "Nearly Tight Convergence Bounds for Semi-Discrete Entropic Optimal Transport." Artificial Intelligence and Statistics, 2022.](https://mlanthology.org/aistats/2022/delalande2022aistats-nearly/)

BibTeX

@inproceedings{delalande2022aistats-nearly,
  title     = {{Nearly Tight Convergence Bounds for Semi-Discrete Entropic Optimal Transport}},
  author    = {Delalande, Alex},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2022},
  pages     = {1619-1642},
  volume    = {151},
  url       = {https://mlanthology.org/aistats/2022/delalande2022aistats-nearly/}
}