Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows
This addresses a computational bottleneck in optimal transport for high-dimensional data, enabling applications in machine learning and statistics.
The paper tackles the problem of efficiently computing optimal transport maps and Wasserstein barycenters in high-dimensional spaces by using conditional normalizing flows, resulting in a method that enables barycenter computation for hundreds of distributions and yields accurate results in experiments.
We present a novel method for efficiently computing optimal transport maps and Wasserstein barycenters in high-dimensional spaces. Our approach uses conditional normalizing flows to approximate the input distributions as invertible pushforward transformations from a common latent space. This makes it possible to directly solve the primal problem using gradient-based minimization of the transport cost, unlike previous methods that rely on dual formulations and complex adversarial optimization. We show how this approach can be extended to compute Wasserstein barycenters by solving a conditional variance minimization problem. A key advantage of our conditional architecture is that it enables the computation of barycenters for hundreds of input distributions, which was computationally infeasible with previous methods. Our numerical experiments illustrate that our approach yields accurate results across various high-dimensional tasks and compares favorably with previous state-of-the-art methods.