Optimal Transport (OT) has recently emerged as a central tool in data sciences to compare
in a geometrically faithful way point clouds and more generally probability distributions. The …

Optimal transport distances have found many applications in machine learning for their
capacity to compare non-parametric probability distributions. Yet their algorithmic complexity …

Sliced Wasserstein distances preserve properties of classic Wasserstein distances while
being more scalable for computation and estimation in high dimensions. The goal of this …

Context.—Machine learning (ML) allows for the analysis of massive quantities of high-
dimensional clinical laboratory data, thereby revealing complex patterns and trends. Thus …

This work investigates the use of robust optimal transport (OT) for shape matching.
Specifically, we show that recent OT solvers improve both optimization-based and deep …

Abstract Existing Optimal Transport (OT) methods mainly derive the optimal transport
plan/matching under the criterion of transport cost/distance minimization, which may cause …

Optimal transport aligns samples across distributions by minimizing the transportation cost
between them, eg, the geometric distances. Yet, it ignores coherence structure in the data …

Optimal transport induces the Earth Mover's (Wasserstein) distance between probability
distributions, a geometric divergence that is relevant to a wide range of problems. Over the …

This paper addresses the problem of Unbalanced Optimal Transport (UOT) in which the
marginal conditions are relaxed (using weighted penalties in lieu of equality) and no …

The Wasserstein distance, rooted in optimal transport (OT) theory, is a popular discrepancy
measure between probability distributions with various applications to statistics and machine …