DeepAI AI Chat
Log In Sign Up

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance

by   Kimia Nadjahi, et al.
Télécom Paris

Minimum expected distance estimation (MEDE) algorithms have been widely used for probabilistic models with intractable likelihood functions and they have become increasingly popular due to their use in implicit generative modeling (e.g. Wasserstein generative adversarial networks, Wasserstein autoencoders). Emerging from computational optimal transport, the Sliced-Wasserstein (SW) distance has become a popular choice in MEDE thanks to its simplicity and computational benefits. While several studies have reported empirical success on generative modeling with SW, the theoretical properties of such estimators have not yet been established. In this study, we investigate the asymptotic properties of estimators that are obtained by minimizing SW. We first show that convergence in SW implies weak convergence of probability measures in general Wasserstein spaces. Then we show that estimators obtained by minimizing SW (and also an approximate version of SW) are asymptotically consistent. We finally prove a central limit theorem, which characterizes the asymptotic distribution of the estimators and establish a convergence rate of √(n), where n denotes the number of observed data points. We illustrate the validity of our theory on both synthetic data and neural networks.


page 1

page 2

page 3

page 4


When OT meets MoM: Robust estimation of Wasserstein Distance

Issued from Optimal Transport, the Wasserstein distance has gained impor...

Geometrical Insights for Implicit Generative Modeling

Learning algorithms for implicit generative models can optimize a variet...

Optimal 1-Wasserstein Distance for WGANs

The mathematical forces at work behind Generative Adversarial Networks r...

Statistical analysis of Wasserstein GANs with applications to time series forecasting

We provide statistical theory for conditional and unconditional Wasserst...

Wasserstein Iterative Networks for Barycenter Estimation

Wasserstein barycenters have become popular due to their ability to repr...

Metropolis-Hastings via Classification

This paper develops a Bayesian computational platform at the interface b...