Some Geometric Calculations on Wasserstein Space
نویسنده
چکیده
We compute the Riemannian connection and curvature for the Wasserstein space of a smooth compact Riemannian manifold.
منابع مشابه
A Geometric Study of the Wasserstein Space of the Line
The concept of optimal transportation raised recently a growing interest in link with the geometry of metric spaces. In particular the L Wasserstein space W (X) have been used in [6] and [8, 9] to define certain curvature conditions on a metric space X. Many useful properties are inherited from X by W (X) (separability, completeness, geodesicness, some non-negative curvature conditions) while s...
متن کاملMetric Currents and Geometry of Wasserstein Spaces
We investigate some geometric aspects of Wasserstein spaces through the continuity equation as worked out in mass transportation theory. By defining a suitable homology on the flat torus T, we prove that the space Pp(T) has non-trivial homology in a metric sense. As a byproduct of the developed tools, we show that every parametrization of a Mather’s minimal measure on T corresponds to a mass mi...
متن کاملOn Wasserstein Geometry of the Space of Gaussian Measures
Abstract. The space which consists of measures having finite second moment is an infinite dimensional metric space endowed with Wasserstein distance, while the space of Gaussian measures on Euclidean space is parameterized by mean and covariance matrices, hence a finite dimensional manifold. By restricting to the space of Gaussian measures inside the space of probability measures, we manage to ...
متن کاملNatural gradient via optimal transport I
We study a natural Wasserstein gradient flow on manifolds of probability distributions with discrete sample spaces. We derive the Riemannian structure for the probability simplex from the dynamical formulation of the Wasserstein distance on a weighted graph. We pull back the geometric structure to the parameter space of any given probability model, which allows us to define a natural gradient f...
متن کاملSliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
In this paper we study generative modeling via autoencoders while using the elegant geometric properties of the optimal transport (OT) problem and the Wasserstein distances. We introduce Sliced-Wasserstein Autoencoders (SWAE), which are generative models that enable one to shape the distribution of the latent space into any samplable probability distribution without the need for training an adv...
متن کامل