Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
- URL: http://arxiv.org/abs/2402.01493v2
- Date: Wed, 15 May 2024 09:17:13 GMT
- Title: Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
- Authors: Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman,
- Abstract summary: Sliced-Wasserstein (SW) distance between probability measures is defined as the average of the Wasserstein resulting for associated one-dimensional projections.
Spherical harmonics are distances on the sphere that form an orthonormal basis of the set of square-integrable functions on the sphere.
An improved rate of convergence, compared to Monte Carlo, is established for general measures.
- Score: 17.237390976128097
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The Sliced-Wasserstein (SW) distance between probability measures is defined as the average of the Wasserstein distances resulting for the associated one-dimensional projections. As a consequence, the SW distance can be written as an integral with respect to the uniform measure on the sphere and the Monte Carlo framework can be employed for calculating the SW distance. Spherical harmonics are polynomials on the sphere that form an orthonormal basis of the set of square-integrable functions on the sphere. Putting these two facts together, a new Monte Carlo method, hereby referred to as Spherical Harmonics Control Variates (SHCV), is proposed for approximating the SW distance using spherical harmonics as control variates. The resulting approach is shown to have good theoretical properties, e.g., a no-error property for Gaussian measures under a certain form of linear dependency between the variables. Moreover, an improved rate of convergence, compared to Monte Carlo, is established for general measures. The convergence analysis relies on the Lipschitz property associated to the SW integrand. Several numerical experiments demonstrate the superior performance of SHCV against state-of-the-art methods for SW distance computation.
Related papers
- Quasi-Monte Carlo for 3D Sliced Wasserstein [39.94228953940542]
We propose quasi-sliced Wasserstein approximations that rely on Quasi-Monte Carlo (QMC) methods.
We empirically evaluate various methods to construct QMC point sets on the 3D unit-hypersphere.
We extend QSW to Quasi-Sliced Wasserstein (RQSW) by randomness in the discussed point sets.
arXiv Detail & Related papers (2023-09-21T01:32:42Z) - Sliced Wasserstein Estimation with Control Variates [47.18652387199418]
Sliced Wasserstein (SW) distances between two probability measures are defined as the expectation of the Wasserstein distance between two one-dimensional projections.
Due to the intractability of the expectation, Monte Carlo integration is performed to estimate the value of the SW distance.
Despite having various variants, there has been no prior work that improves the Monte Carlo estimation scheme for the SW distance.
arXiv Detail & Related papers (2023-04-30T06:03:17Z) - Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation [59.45669299295436]
We propose a Monte Carlo PDE solver for training unsupervised neural solvers.
We use the PDEs' probabilistic representation, which regards macroscopic phenomena as ensembles of random particles.
Our experiments on convection-diffusion, Allen-Cahn, and Navier-Stokes equations demonstrate significant improvements in accuracy and efficiency.
arXiv Detail & Related papers (2023-02-10T08:05:19Z) - Markovian Sliced Wasserstein Distances: Beyond Independent Projections [51.80527230603978]
We introduce a new family of SW distances, named Markovian sliced Wasserstein (MSW) distance, which imposes a first-order Markov structure on projecting directions.
We compare distances with previous SW variants in various applications such as flows, color transfer, and deep generative modeling to demonstrate the favorable performance of MSW.
arXiv Detail & Related papers (2023-01-10T01:58:15Z) - Mean-Square Analysis with An Application to Optimal Dimension Dependence
of Langevin Monte Carlo [60.785586069299356]
This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance.
Our theoretical analysis is further validated by numerical experiments.
arXiv Detail & Related papers (2021-09-08T18:00:05Z) - 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) - Numerical estimation of reachable and controllability sets for a
two-level open quantum system driven by coherent and incoherent controls [77.34726150561087]
The article considers a two-level open quantum system governed by the Gorini--Kossakowski--Lindblad--Sudarshan master equation.
The system is analyzed using Bloch parametrization of the system's density matrix.
arXiv Detail & Related papers (2021-06-18T14:23:29Z) - Finite sample approximations of exact and entropic Wasserstein distances
between covariance operators and Gaussian processes [0.0]
We show that the Sinkhorn divergence between two centered Gaussian processes can be consistently and efficiently estimated.
For a fixed regularization parameter, the convergence rates are it dimension-independent and of the same order as those for the Hilbert-Schmidt distance.
If at least one of the RKHS is finite-dimensional, we obtain a it dimension-dependent sample complexity for the exact Wasserstein distance between the Gaussian processes.
arXiv Detail & Related papers (2021-04-26T06:57:14Z) - Convergence of Gaussian-smoothed optimal transport distance with
sub-gamma distributions and dependent samples [12.77426855794452]
This paper provides convergence guarantees for estimating the GOT distance under more general settings.
A key step in our analysis is to show that the GOT distance is dominated by a family of kernel maximum mean discrepancy distances.
arXiv Detail & Related papers (2021-02-28T04:30:23Z) - 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)
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.