Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples
arXiv:2103.00394
Abstract
The Gaussian-smoothed optimal transport (GOT) framework, recently proposed by Goldfeld et al., scales to high dimensions in estimation and provides an alternative to entropy regularization. This paper provides convergence guarantees for estimating the GOT distance under more general settings. For the Gaussian-smoothed -Wasserstein distance in dimensions, our results require only the existence of a moment greater than . For the special case of sub-gamma distributions, we quantify the dependence on the dimension and establish a phase transition with respect to the scale parameter. We also prove convergence for dependent samples, only requiring a condition on the pairwise dependence of the samples measured by the covariance of the feature map of a kernel space. A key step in our analysis is to show that the GOT distance is dominated by a family of kernel maximum mean discrepancy (MMD) distances with a kernel that depends on the cost function as well as the amount of Gaussian smoothing. This insight provides further interpretability for the GOT framework and also introduces a class of kernel MMD distances with desirable properties. The theoretical results are supported by numerical experiments.
References in corpus (14)
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- Generative Moment Matching Networks
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- Sample Complexity of Sinkhorn divergences
- Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
- Convergence and Concentration of Empirical Measures under Wasserstein Distance in Unbounded Functional Spaces
- Fast Two-Sample Testing with Analytic Representations of Probability Measures
- Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance
- FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test
- Multiscale Strategies for Computing Optimal Transport
- Minimax Distribution Estimation in Wasserstein Distance
- Greedy stochastic algorithms for entropy-regularized optimal transport problems
- Asymptotics of smoothed Wasserstein distances
- Consistent Entropy Estimation for Stationary Time Series