Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We propose to leverage the flexibility of neural networks to learn an approximate optimal transport map. More precisely, we present a new and original method to address the problem of transporting a finite set of samples associated with a first underlying unknown distribution towards another finite set of samples drawn from another unknown distribution. We show that a particular instance of invertible neural networks, namely the normalizing flows, can be used to approximate the solution of this OT problem between a pair of empirical distributions. To this aim, we propose to relax the Monge formulation of OT by replacing the equality constraint on the push-forward measure by the minimization of the corresponding Wasserstein distance. The push-forward operator to be retrieved is then restricted to be a normalizing flow which is trained by optimizing the resulting cost function. This approach allows the transport map to be discretized as a composition of functions. Each of these functions is associated to one sub-flow of the network, whose output provides intermediate steps of the transport between the original and target measures. This discretization yields also a set of intermediate barycenters between the two measures of interest. Experiments conducted on toy examples as well as a challenging task of unsupervised translation demonstrate the interest of the proposed method. Finally, some experiments show that the proposed approach leads to a good approximation of the true OT.
翻译:最佳运输(OT)为比较和绘制概率度量提供了有效的工具。 我们提议利用神经网络的灵活性来学习近似最佳运输图。 更确切地说, 我们提出一种新的和原始的方法来解决将一组有限的样品运输到另一组从另一组未知分布中抽取的有限样品上的问题。 我们表明,一个不可忽略的神经网络的特例,即正常流,可以用来接近一对经验分布之间的这种OT问题的解决办法。 为此,我们提议通过尽量减少相应的瓦塞尔斯坦距离来取代推向措施的平等限制来放松OT的Monge配制。 然后,要检索的推向前操作器将限于一种正常流,通过优化由此产生的成本函数的构成来训练这种正常流。 这种方法使运输图的分解成为功能的构成。 这些功能的每一项功能都与网络的一个子流有关,其输出提供了原始和目标措施之间的运输的中间步骤。 这种离散化还产生一套中间的推进措施,通过尽量减少相应的瓦塞斯坦的距离来取代推向措施的平等限制。 然后,要检索的推向前操作器将限于一个中间的中间压中心, 通过优化的方法, 实验将提出一个拟议的方式展示一个最佳的精确的实验。 展示了两种方法, 将利益。 实验, 实验将展示了两种方法, 以显示为最后的方法, 展示了一种最佳的方法, 展示了一种最佳的方法将利益。