Timezone: »

Stochastic Wasserstein Barycenters
Sebastian Claici · Edward Chien · Justin Solomon

Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ A9

We present a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from optimal transport. Unlike previous approaches, our method extends to continuous input distributions and allows the support of the barycenter to be adjusted in each iteration. We tackle the problem without regularization, allowing us to recover a sharp output whose support is contained within the support of the true barycenter. We give exampleswhere our algorithm recovers a more meaningful barycenter than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.

Author Information

Sebastian Claici (MIT)
Edward Chien (Massachusetts Institute of Technology)
Justin Solomon (MIT)

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

More from the Same Authors