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 2107.07562math.NAcs.NA
收藏

关于Fourier神经算子的泛逼近和误差界

On universal approximation and error bounds for Fourier Neural Operators

Nikola Kovachki, Samuel Lanthaler, Siddhartha Mishra

摘要:

傅立叶神经算子(FNOs)最近被提出作为一个有效的框架,学习运营商之间的映射无限维空间。我们证明了FNO是普遍的,在这个意义上,他们可以近似任何连续运营商所需的精度。此外,我们提出了一种机制,FNOs可以近似运营商与偏微分方程有效。明确的误差界推导表明,FNO的大小,近似运营商与达西型椭圆PDE和不可压缩的Navier-斯托克斯方程的流体动力学,只增加子(log)-线性的倒数的错误。因此,FNO有效地近似运营商产生的一类偏微分方程。

英文摘要:

Fourier neural operators (FNOs) have recently been proposed as an effective framework for learning operators that map between infinite-dimensional spaces. We prove that FNOs are universal, in the sense that they can approximate any continuous operator to desired accuracy. Moreover, we suggest a mechanism by which FNOs can approximate operators associated with PDEs efficiently. Explicit error bounds are derived to show that the size of the FNO, approximating operators associated with a Darcy type elliptic PDE and with the incompressible Navier-Stokes equations of fluid dynamics, only increases sub (log)-linearly in terms of the reciprocal of the error. Thus, FNOs are shown to efficiently approximate operators arising in a large class of PDEs.

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。

↑