Timezone: »

 
Poster
Entropic Gromov-Wasserstein between Gaussian Distributions
Khang Le · Dung Le · Huy Nguyen · · Tung Pham · Nhat Ho

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1103
in Poster Session 3 »

We study the entropic Gromov-Wasserstein and its unbalanced version between (unbalanced) Gaussian distributions with different dimensions. When the metric is the inner product, which we refer to as inner product Gromov-Wasserstein (IGW), we demonstrate that the optimal transportation plans of entropic IGW and its unbalanced variant are (unbalanced) Gaussian distributions. Via an application of von Neumann's trace inequality, we obtain closed-form expressions for the entropic IGW between these Gaussian distributions. Finally, we consider an entropic inner product Gromov-Wasserstein barycenter of multiple Gaussian distributions. We prove that the barycenter is a Gaussian distribution when the entropic regularization parameter is small. We further derive a closed-form expression for the covariance matrix of the barycenter.

Keywords: Theory · T: Learning Theory · T: Optimization

Author Information

Khang Le (The University of Texas at Austin)
Dung Le (École Polytechnique)
Huy Nguyen (University of Texas at Austin)
Tung Pham (VinAI Research)
Nhat Ho (University of Texas at Austin)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors