Stochastic Saddle-Point Optimization for Wasserstein Barycenters

06/11/2020
by   Daniil Tiapkin, et al.
0

We study the computation of non-regularized Wasserstein barycenters of probability measures supported on the finite set. The first result gives a stochastic optimization algorithm for the discrete distribution over the probability measures which is comparable with the current best algorithms. The second result extends the previous one to the arbitrary distribution using kernel methods. Moreover, this new algorithm has a total complexity better than the Stochastic Averaging approach via the Sinkhorn algorithm in many cases.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset