Efficient Transferable Optimal Transport via Min-Sliced Transport Plans

TL;DR

This paper introduces a scalable, transferable min-Sliced Transport Plan framework for optimal transport problems, enabling efficient and effective distribution matching across related tasks with theoretical guarantees and practical benefits.

Contribution

It proposes a novel min-Sliced Transport Plan method that is both scalable and transferable, with theoretical analysis and empirical validation for distribution alignment tasks.

Findings

Optimized slicers remain effective under slight distribution perturbations.

The minibatch formulation provides statistical guarantees on accuracy.

Transferable min-STP achieves strong one-shot matching and supports amortized training.

Abstract

Optimal Transport (OT) offers a powerful framework for finding correspondences between distributions and addressing matching and alignment problems in various areas of computer vision, including shape analysis, image generation, and multimodal tasks. The computation cost of OT, however, hinders its scalability. Slice-based transport plans have recently shown promise for reducing the computational cost by leveraging the closed-form solutions of 1D OT problems. These methods optimize a one-dimensional projection (slice) to obtain a conditional transport plan that minimizes the transport cost in the ambient space. While efficient, these methods leave open the question of whether learned optimal slicers can transfer to new distribution pairs under distributional shift. Understanding this transferability is crucial in settings with evolving data or repeated OT computations across closely related distributions. In this paper, we study the min-Sliced Transport Plan (min-STP) framework and investigate the transferability of optimized slicers: can a slicer trained on one distribution pair yield effective transport plans for new, unseen pairs? Theoretically, we show that optimized slicers remain close under slight perturbations of the data distributions, enabling efficient transfer across related tasks. To further improve scalability, we introduce a minibatch formulation of min-STP and provide statistical guarantees on its accuracy. Empirically, we demonstrate that the transferable min-STP achieves strong one-shot matching performance and facilitates amortized training for point cloud alignment and flow-based generative modeling.