Optimal transport (OT) theory can be informally described using the words of the French
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …

Multimodal learning is a framework for building models that make predictions based on
different types of modalities. Important challenges in multimodal learning are the inference of …

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature
distribution alignment between domains by utilizing the task-specific decision boundary and …

Optimal transport has recently been reintroduced to the machine learning community thanks
in part to novel efficient optimization procedures allowing for medium to large scale …

We study three intriguing properties of contrastive learning. First, we generalize the standard
contrastive loss to a broader family of losses, and we find that various instantiations of the …

Applying image processing algorithms independently to each frame of a video often leads to
undesired inconsistent results over time. Developing temporally consistent video-based …

Transport-based techniques for signal and data analysis have recently received increased
interest. Given their ability to provide accurate generative models for signal intensities and …

The Wasserstein distance and its variations, eg, the sliced-Wasserstein (SW) distance, have
recently drawn attention from the machine learning community. The SW distance …

Domain adaptation is one of the most challenging tasks of modern data analytics. If the
adaptation is done correctly, models built on a specific data representation become more …

This paper introduces a new class of algorithms for optimization problems involving optimal
transportation over geometric domains. Our main contribution is to show that optimal …