arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.12004math.STstat.MLstat.TH
收藏

最优传输映射的熵估计

Entropic estimation of optimal transport maps

Aram-Alexandre Pooladian, Jonathan Niles-Weed

AI总结:

本文提出利用熵最优传输计划的重心投影和 Sinkhorn 算法估计最优传输映射,证明其有限样本性能并给出可自适应光滑性的 Lepski 改进版本。

摘要:

我们开发了一种计算上可行的方法,用于估计定义在 $\mathbb{R}^d$ 上的两个分布之间的最优映射,并给出严格的有限样本保证。借助 Brenier 定理的熵版本,我们证明我们的估计量——最优熵计划的重心投影——可以使用 Sinkhorn 算法轻松计算。因此,不同于当前在维度或样本数量较大时评估缓慢的映射估计方法,我们的方法可并行化,即使对于海量数据集也极其高效。在最优映射满足光滑性假设的条件下,我们证明该估计量具有与文献中其他估计量相当的统计性能,而计算成本却低得多。我们通过数值示例展示了所提出估计量的有效性,即使这些示例并未被我们的假设明确覆盖。借助 Lepski 方法,我们提出了该估计量的一个改进版本,能够自适应于底层最优传输映射的光滑性。我们的证明基于熵最优传输的一种改进对偶原理,以及 Pal (2019) 提出的一种逼近最优熵计划的方法。

英文摘要:

We develop a computationally tractable method for estimating the optimal map between two distributions over $\mathbb{R}^d$ with rigorous finite-sample guarantees. Leveraging an entropic version of Brenier's theorem, we show that our estimator -- the \emph{barycentric projection} of the optimal entropic plan -- is easy to compute using Sinkhorn's algorithm. As a result, unlike current approaches for map estimation, which are slow to evaluate when the dimension or number of samples is large, our approach is parallelizable and extremely efficient even for massive data sets. Under smoothness assumptions on the optimal map, we show that our estimator enjoys comparable statistical performance to other estimators in the literature, but with much lower computational cost. We showcase the efficacy of our proposed estimator through numerical examples, even ones not explicitly covered by our assumptions. By virtue of Lepski's method, we propose a modified version of our estimator that is adaptive to the smoothness of the underlying optimal transport map. Our proofs are based on a modified duality principle for entropic optimal transport and on a method for approximating optimal entropic plans due to Pal (2019).

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。

↑