arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.13422math.STcs.NAmath.NAstat.TH
收藏

三角形输运的稀疏近似。II部分:infinite dimensional案例

Sparse approximation of triangular transports. Part II: the infinite dimensional case

Jakob Zech, Youssef Marzouk

摘要:

对于两个概率测度$ρ$和$π$在$[-1,1]^{\mathbb{N}}$上,我们研究了三角Knothe-Rosenblatt输运$T:[-1,1]^{\mathbb{N}}\to [-1,1]^{\mathbb{N}}$的近似,它将$ρ$推进到$π$ .在适当的假设下,我们证明了$T$可以近似为有理函数,而不会受到维数灾难。我们的结果是适用于后的措施所产生的某些推理问题的未知属于(无限维)巴拿赫空间。特别是,我们表明,它是可以有效地近似采样从某些高维的措施,通过转换一个低维的潜变量。

英文摘要:

For two probability measures $ρ$ and $π$ on $[-1,1]^{\mathbb{N}}$ we investigate the approximation of the triangular Knothe-Rosenblatt transport $T:[-1,1]^{\mathbb{N}}\to [-1,1]^{\mathbb{N}}$ that pushes forward $ρ$ to $π$. Under suitable assumptions, we show that $T$ can be approximated by rational functions without suffering from the curse of dimension. Our results are applicable to posterior measures arising in certain inference problems where the unknown belongs to an (infinite dimensional) Banach space. In particular, we show that it is possible to efficiently approximately sample from certain high-dimensional measures by transforming a lower-dimensional latent variable.

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。

↑