Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions

• URL: http://arxiv.org/abs/2606.30310v1
• Date: Mon, 29 Jun 2026 13:53:29 GMT
• Title: Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions
• Abstract summary: We introduce a new class of estimators for the Sliced Wasserstein distance based on cumulative distribution functions (CDFs) of projected measures.<n>CDFs of projected data can be computed and aggregated locally without requiring the exchange of raw samples.
• Score: 11.346294572963414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Sliced Wasserstein (SW) distance has emerged as a computationally attractive alternative to the Wasserstein distance by leveraging one-dimensional optimal transport along random projections. Standard estimators of the SW distance rely on Monte Carlo averages of one-dimensional Wasserstein distances computed via quantile functions, which require sorting projected samples and access to full datasets. In this work, we introduce a new class of estimators for the Sliced Wasserstein distance based on cumulative distribution functions (CDFs) of projected measures, that avoid sorting and scale via massive dataset parallelism. This class includes several estimators, some of them being indexed by hyperparameters controlling their variance or smoothness. We show that they are especially well suited to scenarios in which CDFs are more tractable than quantile functions, such as mixtures of Gaussians, and moreover that they are also naturally compatible with federated learning, since CDFs of projected data can be computed and aggregated locally without requiring the exchange of raw samples.

Related papers

• Efficient Covariance Estimation for Sparsified Functional Data [51.69796254617083]
  proposed Random-knots (Random-knots-Spatial) and B-spline (Bspline-Spatial) estimators of the covariance function are computationally efficient.<n>Asymptotic pointwise of the covariance are obtained for sparsified individual trajectories under some regularity conditions.
  arXiv  Detail & Related papers  (2025-11-23T00:50:33Z)
• Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances [70.94157767200342]
  We propose a fast estimation method based on regressing Wasserstein distance on sliced Wasserstein distances.<n>We show that accurate models can be learned from a small number of distribution pairs.<n>Our method consistently provides a better approximation of Wasserstein distance than the state-of-the-art Wasserstein embedding model, Wasserstein Wormhole.
  arXiv  Detail & Related papers  (2025-09-24T19:30:53Z)
• Sublinear Algorithms for Wasserstein and Total Variation Distances: Applications to Fairness and Privacy Auditing [7.81603404636933]
  We propose a generic framework to learn the probability and cumulative distribution functions (PDFs and CDFs) of a sub-Weibull.<n>We compute mergeable summaries of distributions from the stream of samples while requiring only sublinear space.<n>Our algorithms significantly improves on the existing methods for distance estimation incurring super-linear time and linear space complexities.
  arXiv  Detail & Related papers  (2025-03-10T18:57:48Z)
• Computing the Distance between unbalanced Distributions -- The flat Metric [0.0]
  We provide an implementation to compute the flat metric in any dimension.<n>Our implementation adapts very well to mass differences and uses them to distinguish between different distributions.
  arXiv  Detail & Related papers  (2023-08-02T09:30:22Z)
• Linearized Wasserstein dimensionality reduction with approximation guarantees [65.16758672591365]
  LOT Wassmap is a computationally feasible algorithm to uncover low-dimensional structures in the Wasserstein space. We show that LOT Wassmap attains correct embeddings and that the quality improves with increased sample size. We also show how LOT Wassmap significantly reduces the computational cost when compared to algorithms that depend on pairwise distance computations.
  arXiv  Detail & Related papers  (2023-02-14T22:12:16Z)
• Wasserstein t-SNE [25.241296604908424]
  We develop an approach for exploratory analysis of hierarchical datasets using the Wasserstein distance metric. We use t-SNE to construct 2D embeddings of the units, based on the matrix of pairwise Wasserstein distances between them.
  arXiv  Detail & Related papers  (2022-05-16T09:09:24Z)
• Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections [19.987683989865708]
  The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications. We propose a new perspective to approximate SW by making use of the concentration of measure phenomenon. Our method does not require sampling a number of random projections, and is therefore both accurate and easy to use compared to the usual Monte Carlo approximation.
  arXiv  Detail & Related papers  (2021-06-29T13:56:19Z)
• Depth-based pseudo-metrics between probability distributions [1.1470070927586016]
  We propose two new pseudo-metrics between continuous probability measures based on data depth and its associated central regions. In contrast to the Wasserstein distance, the proposed pseudo-metrics do not suffer from the curse of dimensionality. The regions-based pseudo-metric appears to be robust w.r.t. both outliers and heavy tails.
  arXiv  Detail & Related papers  (2021-03-23T17:33:18Z)
• On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification [101.0377583883137]
  Projection robust (PR) OT seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances. Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces.
  arXiv  Detail & Related papers  (2020-06-22T14:35:33Z)
• Augmented Sliced Wasserstein Distances [55.028065567756066]
  We propose a new family of distance metrics, called augmented sliced Wasserstein distances (ASWDs) ASWDs are constructed by first mapping samples to higher-dimensional hypersurfaces parameterized by neural networks. Numerical results demonstrate that the ASWD significantly outperforms other Wasserstein variants for both synthetic and real-world problems.
  arXiv  Detail & Related papers  (2020-06-15T23:00:08Z)
• Max-Sliced Wasserstein Distance and its use for GANs [55.09958914575673]
  Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities.<n>We show that the sample complexity of the distance metrics remains one of the factors affecting GAN training.<n>We show that a proposed distance trains GANs on high-dimensional images up to a resolution of 256x256 easily.
  arXiv  Detail & Related papers  (2019-04-11T17:59:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.