The Sinkhorn treatment effect is a new entropic optimal transport measure of divergence between counterfactual distributions that admits first- and second-order pathwise differentiability, debiased estimators, and asymptotically valid tests for distributional treatment effects.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Sinkhorn iterations converge to a Wasserstein mirror gradient flow (the Sinkhorn flow) as regularization epsilon goes to zero with iterations scaled as 1/epsilon.
citing papers explorer
-
Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
The Sinkhorn treatment effect is a new entropic optimal transport measure of divergence between counterfactual distributions that admits first- and second-order pathwise differentiability, debiased estimators, and asymptotically valid tests for distributional treatment effects.
-
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.