Neighbor Embeddings Using Unbalanced Optimal Transport Metrics

With advancements in sensing systems including those in medical imaging like MRI and CT scanners, the advent of the Internet of Things, and cheap abundant data storage, the volume of data collection has grown rapidly. Oftentimes, datasets in these fields contain spatial, temporal, and contextual features, and thus datasets have grown not only in volume, but also in dimensionality and complexity. High-dimensionality can lead to challenges for access, analysis, and interpretation. Without additional assumptions on structure within the data, there is typically some form of the curse of dimensionality that appears in a given task-oriented pipeline. For this reason, many works have explored when and how low-dimensional structures appear in high-dimensional data, and have considered how to detect and utilize such structure effectively for learning [1, 2].