几何光学近似采样:一种反射镜诱导的传输映射框架
Geometric Optics Approximation Sampling: A Reflector-Induced Transport Map Framework
AI总结:
本文提出GOAS框架,利用反射物理定律构造传输映射,仅需目标测度离散近似,经软最小平滑后在多类实验中验证了其采样的准确性与灵活性。
摘要:
本文提出几何光学近似采样(Geometric Optics Approximation Sampling, GOAS),这是一种用于从目标测度中采样的反射镜诱导传输映射框架。一旦构造出反射面,相关的传输映射就可通过反射的物理定律显式确定。作为具体实现,我们开发了一种支撑超椭球构造方法,该方法仅需目标测度的离散近似,无需目标密度的梯度信息。该公式可同时适配基于密度和基于样本的目标表示。我们引入了一种软最小平滑技术,以从该分段超椭球构造中获得平滑的近似传输映射。我们证明了反射镜诱导的推前测度的适定性与稳定性,推导了最大均值差异度量下的定量误差估计,以及连续统计可观测量(包括固定阶矩)的收敛性。对可解析处理的示例、强非高斯目标、基于样本的目标近似以及贝叶斯逆问题的数值实验,验证了GOAS的准确性与灵活性。
英文摘要:
In this paper, we propose Geometric Optics Approximation Sampling (GOAS), a reflector-induced transport-map framework for sampling from target measures. Once a reflecting surface is constructed, the associated transport map is explicitly determined by the physical law of reflection. As a concrete realization, we develop a supporting-hyperellipsoid construction that requires only a discrete approximation of the target measure and does not require gradient information of the target density. The formulation accommodates both density-based and sample-based target representations. A softmin smoothing technique is introduced to obtain a smooth approximate transport map from this piecewise hyperellipsoidal construction. We establish well-posedness and stability of the reflector-induced push-forward measure and derive quantitative error estimates in the maximum mean discrepancy metric, and convergence of continuous statistical observables, including fixed-order moments. Numerical experiments on an analytically tractable example, strongly non-Gaussian targets, sample-based target approximations, and Bayesian inverse problems demonstrate the accuracy and flexibility of GOAS.
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。