Sep 22, 2023 · We further study the Wasserstein gradient flows on GMMs for three typical functionals: potential, internal, and interaction energies. Numerical ...
We study the Wasserstein metric on the Gaussian mixture models (GMMs), which is defined as the pullback of the full Wasserstein metric on the space of ...
Sep 22, 2023 · It is proved that the limit of the Wasserstein metric exists after certain renormalization for a sequence of GMMs whose variances tend to ...
Specifically, for a sequence of GMMs whose variances tend to zero, we prove that the limit of the Wasserstein metric exists after certain renormalization.
Sep 26, 2023 · We further study the Wasserstein gradient flows on GMMs for three typical functionals: potential, internal, and interaction energies. Numerical ...
Jul 27, 2024 · Connected Papers is a visual tool to help researchers and applied scientists find academic papers relevant to their field of work.
Co-authors ; Scaling Limits of the Wasserstein information matrix on Gaussian Mixture Models. W Li, J Zhao. arXiv preprint arXiv:2309.12997, 2023. 2, 2023.
People also ask
What is the limitation of Gaussian mixture model?
What is the problem with Gaussian mixture model?
What is the Gaussian mixture model of distribution?
What is the Gaussian mixture model for time series clustering?
We consider the Wasserstein metric on the Gaussian mixture models (GMMs), which is defined as the pullback of the full Wasserstein metric on the space of smooth ...
An optimal mass transport framework on the space of Gaussian mixture models as a submanifold of probability densities equipped with the Wasserstein metric ...
Specifically, for a sequence of GMMs whose variances tend to zero, we prove that the limit of the Wasserstein metric exists after certain renormalization.