Uncertainty in Artificial Intelligence · 2019 · 54 citations · 18 references
ComputingComputer ScienceMathematicsAlgorithmsMachine LearningOptimizationApproximation AlgorithmsApproximation MethodsConvex OptimizationGenerative ModelingOptimization For Machine LearningStochastic OptimizationComputational Complexity Of AlgorithmsNumerical Stability AnalysisOptimal TransportProximal AlgorithmsRegularizationRegularization Techniques
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, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms. We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. The algorithm (a) converges to exact Wasserstein distance with theoretical guarantee and robust regularization parameter selection, (b) alleviates numerical stability issue, (c) has similar computational complexity to Sinkhorn, and (d) avoids the shrinking problem when apply to generative models. Furthermore, a new algorithm is proposed based on IPOT to obtain sharper Wasserstein barycenter.
18
Erik Reinhard, M. Adhikhmin, Bryan N S Gooch et al. · IEEE Computer Graphics and Applications · 2001 · 3K citations
Arts, Vision Science, Color Theory +10
Sinkhorn Distances: Lightspeed Computation of Optimal Transport
Marco Cuturi · 2013 · 2.2K citations