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 2302.13965math.NAcs.NAmath.STstat.TH
收藏

测度传输采样算法的逼近理论框架

An Approximation Theory Framework for Measure-Transport Sampling Algorithms

Ricardo Baptista, Bamdad Hosseini, Nikola B. Kovachki, Youssef M. Marzouk, Amir Sagiv

AI总结:

该研究提出分析测度传输采样算法的通用逼近理论框架,推导连续极限下的先验误差估计与新稳定性估计,给出多种度量下的收敛速率,并通过数值实验验证拓展理论。

摘要:

本文提出了一个通用的逼近理论框架,用于分析概率建模中的测度传输算法。这类算法的核心驱动应用是采样——这是统计推断与生成式建模中的核心任务。我们在连续极限下(即测度(或其密度)已知,但传输映射通过有限维函数空间进行离散化或逼近时)给出了先验误差估计。我们的分析依托传输映射的正则性理论与高维函数的经典逼近理论。分析的第三个具有独立研究价值的要素是新的稳定性估计的构建,这类估计将两个映射之间的距离与它们所定义的推前测度之间的距离(或散度)关联起来。我们展示了该框架的一系列应用,针对实际问题,利用Wasserstein度量、最大平均偏差(maximum mean discrepancy)以及Kullback–Leibler散度得到了定量收敛速率。我们还针对广泛使用的三角Knöthe-Rosenblatt映射的逼近推导了专门的速率,并通过数值实验验证并拓展了我们的理论。

英文摘要:

This article presents a general approximation-theoretic framework to analyze measure transport algorithms for probabilistic modeling. A primary motivating application for such algorithms is sampling -- a central task in statistical inference and generative modeling. We provide a priori error estimates in the continuum limit, i.e., when the measures (or their densities) are given, but when the transport map is discretized or approximated using a finite-dimensional function space. Our analysis relies on the regularity theory of transport maps and on classical approximation theory for high-dimensional functions. A third element of our analysis, which is of independent interest, is the development of new stability estimates that relate the distance between two maps to the distance~(or divergence) between the pushforward measures they define. We present a series of applications of our framework, where quantitative convergence rates are obtained for practical problems using Wasserstein metrics, maximum mean discrepancy, and Kullback--Leibler divergence. Specialized rates for approximations of the popular triangular Kn{ö}the-Rosenblatt maps are obtained, followed by numerical experiments that demonstrate and extend our theory.

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。

↑