Results 31 to 40 of about 1,392,762 (281)
CoRR, 2020 Optimal transport (OT) is a powerful geometric and probabilistic tool for finding correspondences and measuring similarity between two distributions. Yet, its original formulation relies on the existence of a cost function between the samples of the two distributions, which makes it impractical when they are supported on different spaces. To circumvent
Redko, Ievgen +3 more
openaire +4 more sources
Immiscible color flows in optimal transport networks for image classification
Frontiers in Physics, 2023 In classification tasks, it is crucial to meaningfully exploit the information contained in the data. While much of the work in addressing these tasks is focused on building complex algorithmic infrastructures to process inputs in a black-box fashion ...
Alessandro Lonardi +2 more
doaj +1 more source
CoRR, 2017 Optimal Transport has recently gained interest in machine learning for applications ranging from domain adaptation, sentence similarities to deep learning. Yet, its ability to capture frequently occurring structure beyond the "ground metric" is limited.
David Alvarez-Melis +2 more
openaire +3 more sources
Unbalanced CO-optimal Transport
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 Optimal transport (OT) compares probability distributions by computing a meaningful alignment between their samples. CO-optimal transport (COOT) takes this comparison further by inferring an alignment between features as well. While this approach leads to better alignments and generalizes both OT and Gromov-Wasserstein distances, we provide a ...
Tran, Quang Huy +6 more
openaire +2 more sources
Constrained Optimal Transport [PDF]
Archive for Rational Mechanics and Analysis, 2017 The classical duality theory of Kantorovich and Kellerer for the classical optimal transport is generalized to an abstract framework and a characterization of the dual elements is provided. This abstract generalization is set in a Banach lattice $\cal{X}$ with a order unit.
Ibrahim Ekren, H. Mete Soner
openaire +3 more sources
The intrinsic dynamics of optimal transport [PDF]
, 2015 The question of which costs admit unique optimizers in the Monge-Kantorovich problem of optimal transportation between arbitrary probability densities is investigated. For smooth costs and densities on compact manifolds, the only known examples for which
McCann, Robert J., Rifford, Ludovic
core +7 more sources
Quantum Optimal Transport is Cheaper [PDF]
Journal of Statistical Physics, 2020 We compare bipartite (Euclidean) matching problems in classical and quantum mechanics. The quantum case is treated in terms of a quantum version of the Wasserstein distance introduced in [F. Golse, C. Mouhot, T. Paul, Commun. Math. Phys. 343 (2016), 165-205]. We show that the optimal quantum cost can be cheaper than the classical one.
Caglioti E., Golse F., Paul T.
openaire +4 more sources
Optimal transport for Gaussian mixture models [PDF]
, 2018 We present an optimal mass transport framework on the space of Gaussian mixture models, which are widely used in statistical inference. Our method leads to a natural way to compare, interpolate and average Gaussian mixture models.
Chen, Yongxin +2 more
core +2 more sources
Simultaneous Control of Cost Dynamics and Transport in Network Systems
IEEE AccessTransportation networks, including infrastructures such as roads and power transmission, are crucial for supporting modern society. However, these networks are frequently exposed to risks such as natural disasters, e.g., earthquakes and hurricanes.
Koshi Oishi +5 more
doaj +1 more source
Computational Optimal Transport
Found. Trends Mach. Learn., 2018 new version with corrected typo in Eq.
Gabriel Peyré, Marco Cuturi
openaire +2 more sources