arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1901.08686math.OCcs.DS
收藏

关于Wasserstein重心逼近的复杂性

On the Complexity of Approximating Wasserstein Barycenter

Alexey Kroshnin, Darina Dvinskikh, Pavel Dvurechensky, Alexander Gasnikov, Nazarii Tupitsa, Cesar Uribe

摘要:

我们研究的复杂性近似Wassertein重心的$m$离散措施,或直方图的大小$n$通过对比两种替代方法,都使用熵正则化。第一种方法是基于迭代Bregman投影(IBP)算法,我们的新的分析给出了一个复杂度界成正比的$\frac{mn^2}{\varepsilon^2}$近似原始的非正则重心。使用另一种基于加速梯度下降的方法,我们获得了与$\frac{mn^{2.5}}{\varepsilon} $成比例的复杂度。作为一个副产品,我们表明,在这两种方法中的正则化参数必须是成比例的$\varepsilon$,这将导致不稳定的两种算法时,所需的精度是高的。为了克服这个问题,我们提出了一种新的近似IBP算法,它可以被看作是一个近似的梯度法,它使用IBP在每一次迭代,使一个近似的步骤。我们还考虑了这些算法的可扩展性问题,从分布式优化的方法,并表明,第一个算法可以实现在一个集中的分布式设置(主/从),而第二个是服从一个更一般的分散的分布式设置与任意的网络拓扑结构。

英文摘要:

We study the complexity of approximating Wassertein barycenter of $m$ discrete measures, or histograms of size $n$ by contrasting two alternative approaches, both using entropic regularization. The first approach is based on the Iterative Bregman Projections (IBP) algorithm for which our novel analysis gives a complexity bound proportional to $\frac{mn^2}{\varepsilon^2}$ to approximate the original non-regularized barycenter. Using an alternative accelerated-gradient-descent-based approach, we obtain a complexity proportional to $\frac{mn^{2.5}}{\varepsilon} $. As a byproduct, we show that the regularization parameter in both approaches has to be proportional to $\varepsilon$, which causes instability of both algorithms when the desired accuracy is high. To overcome this issue, we propose a novel proximal-IBP algorithm, which can be seen as a proximal gradient method, which uses IBP on each iteration to make a proximal step. We also consider the question of scalability of these algorithms using approaches from distributed optimization and show that the first algorithm can be implemented in a centralized distributed setting (master/slave), while the second one is amenable to a more general decentralized distributed setting with an arbitrary network topology.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑