# Sliced Orlicz-Wasserstein

arXiv: https://arxiv.org/abs/2609.32847 · HTML: https://mlsanity.com/paper/2609.32847/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 67 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Sinkhorn-Drifting Generative Models](https://mlsanity.com/paper/2603.12366/) (2026)
- [A Practical Introduction to Kernel Discrepancies: MMD, HSIC & KSD](https://mlsanity.com/paper/2503.04820/) (2025)
- [Optimal Transport for Machine Learners](https://mlsanity.com/paper/2505.06589/) (2025)
- [MIND: Monge Inception Distance for Generative Models Evaluation](https://mlsanity.com/paper/2605.06797/) (2026)

## Abstract (arXiv)

We propose sliced Orlicz-Wasserstein (SOW) distance which is a generalization of sliced Wasserstein (SW) distance. SOW replaces the Lp norm in SW with a Luxemburg norm cost induced by an Orlicz function φ. 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)=xp. 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.