Wasserstein metric


In mathematics, the Wasserstein or Kantorovich–Rubinstein metric or distance is a distance function defined between probability distributions on a given metric space.
Intuitively, if each distribution is viewed as a unit amount of "dirt" piled on , the metric is the minimum "cost" of turning one pile into the other, which is assumed to be the amount of dirt that needs to be moved times the mean distance it has to be moved. Because of this analogy, the metric is known in computer science as the earth mover's distance.
The name "Wasserstein distance" was coined by R. L. Dobrushin in 1970, after the Russian mathematician Leonid Vaseršteĭn who introduced the concept in 1969. Most English-language publications use the German spelling "Wasserstein".

Definition

Let be a metric space for which every probability measure on ' is a Radon measure. For, let denote the collection of all probability measures on ' with finite moment. Then, there exists some in ' such that:
The Wasserstein distance between two probability measures ' and in is defined as
where denotes the collection of all measures on with marginals ' and ' on the first and second factors respectively.
The above distance is usually denoted or . The remainder of this article will use the ' notation.
The Wasserstein metric may be equivalently defined by
where denotes the expected value of a random variable and the infimum is taken over all joint distributions of the random variables and with marginals ' and respectively.

Intuition and connection to optimal transport

One way to understand the motivation of the above definition is to consider the optimal transport problem. That is, for a distribution of mass on a space, we wish to transport the mass in such a way that it is transformed into the distribution on the same space; transforming the 'pile of earth' to the pile. This problem only makes sense if the pile to be created has the same mass as the pile to be moved; therefore without loss of generality assume that and are probability distributions containing a total mass of 1. Assume also that there is given some cost function
that gives the cost of transporting a unit mass from the point to the point.
A transport plan to move into can be described by a function which gives the amount of mass to move from to. You can imagine the task as the need to move a pile of earth of shape to the hole in the ground of shape such that at the end, both the pile of earth and the hole in the ground completely vanish. In order for this plan to be meaningful, it must satisfy the following properties
That is, that the total mass moved out of an infinitesimal region around must be equal to and the total mass moved into a region around must be. This is equivalent to the requirement that be a joint probability distribution with marginals and. Thus, the infinitesimal mass transported from to is, and the cost of moving is, following the definition of the cost function. Therefore, the total cost of a transport plan is
The plan is not unique; the optimal transport plan is the plan with the minimal cost out of all possible transport plans. As mentioned, the requirement for a plan to be valid is that it is a joint distribution with marginals and ; letting denote the set of all such measures as in the first section, the cost of the optimal plan is
If the cost of a move is simply the distance between the two points, then the optimal cost is identical to the definition of the distance.

Examples

Point masses (degenerate distributions)

Let and be two degenerate distributions located at points and in. There is only one possible coupling of these two measures, namely the point mass located at. Thus, using the usual absolute value function as the distance function on, for any, the -Wasserstein distance between and is
By similar reasoning, if and are point masses located at points and in, and we use the usual Euclidean norm on as the distance function, then

Normal distributions

Let and be two non-degenerate Gaussian measures on, with respective expected values and and symmetric positive semi-definite covariance matrices and. Then, with respect to the usual Euclidean norm on, the 2-Wasserstein distance between and is
This result generalises the earlier example of the Wasserstein distance between two point masses, since a point mass can be regarded as a normal distribution with covariance matrix equal to zero, in which case the trace term disappears and only the term involving the Euclidean distance between the means remains.

Applications

The Wasserstein metric is a natural way to compare the probability distributions of two variables X and Y, where one variable is derived from the other by small, non-uniform perturbations.
In computer science, for example, the metric W1 is widely used to compare discrete distributions, e.g. the color histograms of two digital images; see earth mover's distance for more details.
In their paper 'Wasserstein GAN', Arjovsky et al. use the Wasserstein-1 metric as a way to improve the original framework of Generative Adversarial Networks, to alleviate the vanishing gradient and the mode collapse issues.

Properties

Metric structure

It can be shown that Wp satisfies all the axioms of a metric on Pp. Furthermore, convergence with respect to Wp is equivalent to the usual weak convergence of measures plus convergence of the first pth moments.

Dual representation of ''W''1

The following dual representation of W1 is a special case of the duality theorem of Kantorovich and Rubinstein : when μ and ν have bounded support,
where Lip denotes the minimal Lipschitz constant for f.
Compare this with the definition of the Radon metric:
If the metric d is bounded by some constant C, then
and so convergence in the Radon metric implies convergence in the Wasserstein metric, but not vice versa.

Equivalence of W2 and a negative-order Sobolev norm

Under suitable assumptions, the Wasserstein distance of order two is Lipschitz equivalent to a negative-order homogeneous Sobolev norm. More precisely, if we take to be a connected Riemannian manifold equipped with a positive measure, then we may define for the seminorm
and for a signed measure on the dual norm
Then any two probability measures and on satisfy the upper bound
In the other direction, if and each have densities with respect to the standard volume measure on that are both bounded above some, and has non-negative Ricci curvature, then

Separability and completeness

For any p ≥ 1, the metric space is separable, and is complete if is separable and complete.