We present a short and elementary proof of the duality for Wasserstein distributionally robust optimization, which holds for any arbitrary Kantorovich transport distance, any arbitrary measurable loss function, and any arbitrary nominal probability distribution, as long as certain interchangeability principle holds.
翻译:我们提出一个简短和基本的证据,证明瓦森斯坦分配上强有力的优化的双重性,只要某些可互换性原则坚持,它就具有任意的康托罗维奇运输距离、任意的可计量损失功能和任意的名义概率分布。