Results 21 to 30 of about 4,469 (193)
Earth mover’s distance as a measure of CP violation
Journal of High Energy Physics, 2023 We introduce a new unbinned two sample test statistic sensitive to CP violation utilizing the optimal transport plan associated with the Wasserstein (earth mover’s) distance.
Adam Davis +3 more
doaj +1 more source
Multimedia Analysis and Fusion via Wasserstein Barycenter
International Journal of Networked and Distributed Computing (IJNDC), 2020 Optimal transport distance, otherwise known as Wasserstein distance, recently has attracted attention in music signal processing and machine learning as powerful discrepancy measures for probability distributions.
Cong Jin +7 more
doaj +1 more source
Fused Gromov-Wasserstein Distance for Structured Objects
Algorithms, 2020 Optimal transport theory has recently found many applications in machine learning thanks to its capacity to meaningfully compare various machine learning objects that are viewed as distributions.
Titouan Vayer +4 more
doaj +1 more source
Free complete Wasserstein algebras [PDF]
Logical Methods in Computer Science, 2018 We present an algebraic account of the Wasserstein distances $W_p$ on complete metric spaces, for $p \geq 1$. This is part of a program of a quantitative algebraic theory of effects in programming languages.
Radu Mardare +2 more
doaj +1 more source
On a linearization of quadratic Wasserstein distance
CoRR, 2022 This paper studies the problem of computing a linear approximation of quadratic Wasserstein distance $W_2$. In particular, we compute an approximation of the negative homogeneous weighted Sobolev norm whose connection to Wasserstein distance follows from a classic linearization of a general Monge-Ampére equation. Our contribution is threefold.
Philip Greengard +3 more
openaire +2 more sources
CoRR, 2019 The Wasserstein distance is a powerful metric based on the theory of optimal transport. It gives a natural measure of the distance between two distributions with a wide range of applications. In contrast to a number of the common divergences on distributions such as Kullback-Leibler or Jensen-Shannon, it is (weakly) continuous, and thus ideal for ...
Jung Hun Oh +5 more
openaire +2 more sources
Big Data and Cognitive Computing, 2022 Large retail companies routinely gather huge amounts of customer data, which are to be analyzed at a low granularity. To enable this analysis, several Key Performance Indicators (KPIs), acquired for each customer through different channels are associated
Andrea Ponti +4 more
doaj +1 more source
Matricial Wasserstein-1 Distance [PDF]
IEEE Control Systems Letters, 2017 In this note, we propose an extension of the Wasserstein 1-metric ($W_1$) for matrix probability densities, matrix-valued density measures, and an unbalanced interpretation of mass transport. The key is using duality theory, in particular, a "dual of the dual" formulation of $W_1$.
Yongxin Chen 0002 +3 more
openaire +5 more sources
Graph Diffusion Wasserstein Distances [PDF]
, 2021 Optimal Transport (OT) for structured data has received much attention in the machine learning community, especially for addressing graph classification or graph transfer learning tasks. In this paper, we present the Diffusion Wasserstein (DW) distance, as a generalization of the standard Wasserstein distance to undirected and connected graphs where ...
Barbe, Amélie +4 more
openaire +1 more source
Subspace Robust Wasserstein Distances
CoRR, 2019 Making sense of Wasserstein distances between discrete measures in high-dimensional settings remains a challenge. Recent work has advocated a two-step approach to improve robustness and facilitate the computation of optimal transport, using for instance projections on random real lines, or a preliminary quantization of the measures to reduce the size ...
François-Pierre Paty, Marco Cuturi
openaire +3 more sources