Jun 12, 2020 · This paper provides a first step into a computational theory of the PRW distance and provides the links between optimal transport and Riemannian optimization.
This paper provides a first step into a computational theory of the PRW distance and provides the links between optimal transport and Riemannian optimization. 1 ...
Dec 6, 2020 · This paper provides a first step into a computational theory of the PRW distance and provides the links between optimal transport and Riemannian ...
Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit (WPP), is a robust variant of the Wasserstein distance.
This paper introduces a novel methodology to efficiently compute PRW (of order 2, based on the Euclidean distance) between finite discrete probability measures: ...
"Projection Robust Wasserstein Distance and Riemannian Optimization." in NeurIPS'20. Requirements. python 3.7+, Numpy, Scikit-learn. Citation. This repository ...
A first step into a computational theory of the PRW distance is provided and the links between optimal transport and Riemannian optimization are provided.
People also ask
What is Wasserstein distance distributionally robust optimization?
What is the Wasserstein projection?
This paper provides a first step into a computational theory of the PRW distance and provides the links between optimal transport and Riemannian optimization. 1 ...
Dec 6, 2020 · A multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster ...
Nov 24, 2022 · The obtained maximized distance is referred to as projection robust Wasserstein (PRW) distance. In this paper, we equivalently reformulate the ...