Arbitrary Distributions Mapping via SyMOT-Flow: A Flow-based Approach Integrating Maximum Mean Discrepancy and Optimal Transport

TL;DR

SyMOT-Flow is a novel flow-based model that learns transformations between unknown distributions by minimizing symmetric MMD and incorporating optimal transport, improving stability and interpretability in sample generation.

Contribution

Introduces SyMOT-Flow, a new invertible transformation model combining symmetric MMD and optimal transport regularization for better distribution mapping.

Findings

More stable sample generation

Effective in high-dimensional medical image synthesis

Theoretical guarantees for the proposed model

Abstract

Finding a transformation between two unknown probability distributions from finite samples is crucial for modeling complex data distributions and performing tasks such as sample generation, domain adaptation and statistical inference. One powerful framework for such transformations is normalizing flow, which transforms an unknown distribution into a standard normal distribution using an invertible network. In this paper, we introduce a novel model called SyMOT-Flow that trains an invertible transformation by minimizing the symmetric maximum mean discrepancy between samples from two unknown distributions, and an optimal transport cost is incorporated as regularization to obtain a short-distance and interpretable transformation. The resulted transformation leads to more stable and accurate sample generation. Several theoretical results are established for the proposed model and its effectiveness is validated with low-dimensional illustrative examples as well as high-dimensional bi-modality medical image generation through the forward and reverse flows.