stat.MLSep 26, 2026

Sliced Orlicz-Wasserstein

Authors: Binh Thuan Tran, Khai Nguyen

Organizations: LAMA, LIGM, Université Gustave Eiffel · Department of Statistics and Data Science, Texas A&M University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

We propose sliced Orlicz-Wasserstein (SOW) distance which is a generalization of sliced Wasserstein (SW) distance. SOW replaces the LpL^p norm in SW with a Luxemburg norm cost induced by an Orlicz function φφ. First, we prove that SOW distance is a metric on the space of measures with finite Orlicz norm, and show that it recovers the SW distance when the Orlicz function is φ(x)=xpφ(x)=x^p. Next, we derive the topological properties of the SOW distance. In particular, we show that convergence under SOW implies weak convergence, and the converse is true under the compact support condition. We then present the theoretical results for estimating the SOW distance. We derive sample complexity for both the distance itself and the powered functional of the distance, and prove their minimax optimality. In addition, we discuss the computational algorithm for approximating the SOW distance by Monte-Carlo estimation and bisection search, as well as the associated approximation error and computational complexity analysis. Our experimental results reveal the superior computational efficiency of SOW compared with Orlicz-Wasserstein (OW) distance. Also, in the experiments, we demonstrate the favorable flexibility of SOW distance over SW in detecting differences between distributions by comparing their performance in two-sample tests and evaluating generative models on image datasets.

Figures & tables

Figure 1: Computational speed of SOW and OW.
Figure 2: Sample and Monte Carlo projection errors of SW and SOW, and bisection error of SOW.
Figure 3: Power versus sample-size: synthetic data, MNIST and CIFAR-10 versus CIFAR-10.1.
Figure 4: Evaluating generative models with SW and SOW.
More in this topic

Optimal Transport

Optimal transport compares and transforms probability distributions by finding low-cost ways to move mass between them.

See all 287 papers

Explore similar work

CardsList
Jun 29, 2026

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

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.

Christophe Vauthier, Quentin Mérigot, Anna Korba

Laboratoire de Mathématiques d’Orsay, Université Paris-Saclay Gif-sur-Yvette, France · Centre de recherche en économie et statistique, ENSAE Palaiseau, France

Sliced Wasserstein DistanceOptimal TransportWasserstein Distance
AskPDF
Oct 14, 2026

Vertical Sliced Wasserstein Distances for Meta-Measures

Many modern learning problems require comparing probability distributions whose individual observations are themselves probability measures, naturally giving rise to meta-measures in P(P(Ω))\mathcal{P}(\mathcal{P}(Ω)). However, optimal transport distances on this space can be prohibitively expensive to evaluate. We introduce the vertical sliced Wasserstein (VSW\mathrm{VSW}) distance, a scalable metric on P(P(Ω))\mathcal{P}(\mathcal{P}(Ω)). Rather than slicing along the transport geometry of P(Ω)\mathcal{P}(Ω), VSW\mathrm{VSW} projects each inner measure using continuous test functions and compares the resulting one-dimensional distributions with one-dimensional Wasserstein distance. We prove that VSW\mathrm{VSW} is a valid metric on P(P(Ω))\mathcal{P}(\mathcal{P}(Ω)), metrizes weak convergence, and admits dimension-independent statistical convergence guarantees. Empirically, VSW\mathrm{VSW} provides high accuracy and efficiency compared with existing distances for meta-measures. We further derive a practical particle gradient for the empirical VSW22\mathrm{VSW}_2^2 objective and demonstrate its use for gradient-based transport of meta-measures. VSW\mathrm{VSW} provides a simple and scalable alternative for comparing and optimizing distributions of distributions.

Elaheh Akbari, Ahmadreza Moradipari, Kyungtae Han +4

College of Connected Computing, Vanderbilt University · Toyota Motor North America, InfoTech Labs · Department of Computer Science, University of California, Davis +2

Wasserstein DistanceOptimal TransportSliced Wasserstein Distance
AskPDF
May 11, 2026

The Observable Wasserstein Distance

We introduce the observable Wasserstein distance, a framework for deriving lower bounds on the Wasserstein distance between probability measures on Polish metric spaces, designed to bypass the computational intractability of exact optimal transport in large-scale, non-Euclidean datasets. Analogous to the sliced Wasserstein distance in Rd\mathbb{R}^d, our approach projects measures onto the real line via 1-Lipschitz observables and computes the Wasserstein distances between the resulting pushforward distributions. We define a hierarchy of pseudo-metrics by restricting observables to a nested chain of subspaces. A central theoretical contribution is an injectivity result linking the metric covering dimension of the support of a measure to the specific order in the hierarchy that guarantees unique recovery. This serves as a metric-space analogue to the Cramér-Wold Device for Euclidean distributions. We demonstrate that this hierarchy offers a tunable trade-off between sharpness as a lower bound on the Wasserstein distance and computational efficiency. We also present a discrete computational model for finite grids and numerical experiments validating the efficacy and utility of these approximations.

Edivaldo Lopes dos Santos, Leandro Vicente Mauri, Washington Mio +1

1Departamento de Matem´atica, Universidade Federal de S˜ao Carlos, Brazil · Department of Mathematics, Florida State University, USA

Sliced Wasserstein DistanceOptimal TransportWasserstein Distance
AskPDF