构造性量子化:经验测度近似
Constructive quantization: approximation by empirical measures
摘要:
本文研究了概率测度$μ$在$\mathbb{R}^{d}$上的经验测度$\hatμ_{N}$作为随机量子化的逼近.作为误差准则,我们考虑一个平均的$p$ -th时刻Wasserstein度量。在$2p<d$的情况下,我们建立了精确的误差上界和下界,一个高分辨率的公式。此外,我们提供了一个通用的估计的基础上的时刻,所谓的皮尔斯型估计。特别是,我们表明,量化的经验措施是最佳的顺序弱假设下。
英文摘要:
In this article, we study the approximation of a probability measure $μ$ on $\mathbb{R}^{d}$ by its empirical measure $\hatμ_{N}$ interpreted as a random quantization. As error criterion we consider an averaged $p$-th moment Wasserstein metric. In the case where $2p<d$, we establish refined upper and lower bounds for the error, a high-resolution formula. Moreover, we provide a universal estimate based on moments, a so-called Pierce type estimate. In particular, we show that quantization by empirical measures is of optimal order under weak assumptions.
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。