Sublinear Algorithms for Wasserstein and Total Variation Distances: Applications to Fairness and Privacy Auditing

Resource-efficiently computing representations of probability distributions and the distances between them while only having access to the samples is a fundamental and useful problem across mathematical sciences. In this paper, we propose a generic algorithmic framework to estimate the PDF and CDF of any sub-Gaussian distribution while the samples from them arrive in a stream. We compute mergeable summaries of distributions from the stream of samples that require sublinear space w.r.t. the number of observed samples. This allows us to estimate Wasserstein and Total Variation (TV) distances between any two sub-Gaussian distributions while samples arrive in streams and from multiple sources (e.g. federated learning). Our algorithms significantly improves on the existing methods for distance estimation incurring super-linear time and linear space complexities. In addition, we use the proposed estimators of Wasserstein and TV distances to audit the fairness and privacy of the ML algorithms. We empirically demonstrate the efficiency of the algorithms for estimating these distances and auditing using both synthetic and real-world datasets.

@article{basu2025_2503.07775,
  title={ Sublinear Algorithms for Wasserstein and Total Variation Distances: Applications to Fairness and Privacy Auditing },
  author={ Debabrota Basu and Debarshi Chanda },
  journal={arXiv preprint arXiv:2503.07775},
  year={ 2025 }
}