Private Wasserstein Distance with Random Noises

arXiv:2404.06787v1 Announce Type: new
Abstract: Wasserstein distance is a principle measure of data divergence from a distributional standpoint. However, its application becomes challenging in the context of data privacy, where sharing raw data is restricted. Prior attempts have employed techniques like Differential Privacy or Federated optimization to approximate Wasserstein distance. Nevertheless, these approaches often lack accuracy and robustness against potential attack. In this study, we investigate the underlying triangular properties within the Wasserstein space, leading to a straightforward solution named …

abstract application arxiv context cs.ai cs.lg data data privacy differential differential privacy divergence however optimization prior privacy random raw type