Spherical Sliced-Wasserstein
arXiv:2206.08780
Abstract
Many variants of the Wasserstein distance have been introduced to reduce its original computational burden. In particular the Sliced-Wasserstein distance (SW), which leverages one-dimensional projections for which a closed-form solution of the Wasserstein distance is available, has received a lot of interest. Yet, it is restricted to data living in Euclidean spaces, while the Wasserstein distance has been studied and used recently on manifolds. We focus more specifically on the sphere, for which we define a novel SW discrepancy, which we call spherical Sliced-Wasserstein, making a first step towards defining SW discrepancies on manifolds. Our construction is notably based on closed-form solutions of the Wasserstein distance on the circle, together with a new spherical Radon transform. Along with efficient algorithms and the corresponding implementations, we illustrate its properties in several machine learning use cases where spherical representations of data are at stake: sampling on the sphere, density estimation on real earth data or hyperspherical auto-encoders.
Published as a conference paper at ICLR 2023
References in corpus (16)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Bootstrap your own latent: A new approach to self-supervised Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
- Normalizing Flows on Riemannian Manifolds
- Riemannian Continuous Normalizing Flows
- The Power Spherical distribution
- A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
- Augmented Sliced Wasserstein Distances
- Amortized Projection Optimization for Sliced Wasserstein Generative Models
- Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution
- Aligning Hyperbolic Representations: an Optimal Transport-based approach
- On the Minkowski-Funk Transform
- Riemannian Langevin Algorithm for Solving Semidefinite Programs
- Sliced Wasserstein Variational Inference
- Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev