A Fast Proximal Point Method for Wasserstein Distance
share
Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, several important machine learning applications call for the computation of exact Wasserstein distance, and regularized variations with small regularization parameter will fail due to numerical stability issues or degradate the performance. We address this challenge by developing an Inexact Proximal point method for Optimal Transport (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. We also simplify the architecture for learning generative models based on optimal transport solution, and generalize the idea of IPOT to a new method for computing Wasserstein barycenter. We provide convergence analysis of IPOT and experiments showing our new methods outperform the state-of-the-art methods in terms of both effectiveness and efficiency.
READ FULL TEXT
