On the Kantorovich–Rubinstein theorem

111 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Statistical Approximating Distributions Under Differential Privacy (2018, methodology): “We use its dual representation [Edwards, 2011]: Definition 3.6 (Wasserstein distance).”
Robust Optimization for Fairness with Noisy Protected Groups (2020, methodology): “alistic scenario where the noisy groups are generated from a proxy feature, combined with some prior knowledge. We use the Boston Stop-and-frisk dataset released by the Boston Police Department (BPD) [2], which includes data from individuals observed, interrogated, approach achieves lower error rat”
On the regularization of Wasserstein GANs (2017, unknown): “Theorem 1 by Goodfellow et al. (2014) shows that, if the optimal discriminator is found in each iteration, minimization of the resulting loss function of the generator leads to minimization of the Jensen-Shannon (JS) divergence.”