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 2607.00320stat.MLcs.LGcs.NAmath.NA
收藏

从谱方法到傅里叶神经算子的样本复杂度界

From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators

University of Chicago(芝加哥大学)

Nisha Chandramoorthy, Daniel Sanz-Alonso, Nathan Waniorek

AI总结:

针对耗散演化方程的解算子,证明傅里叶神经算子(FNO)在谱离散化下可实现高效逼近与学习,给出逼近误差界和多项式样本复杂度保证,并推广至Navier-Stokes等方程。

摘要:

我们为应用于耗散演化方程的时间$T$解算子的傅里叶神经算子(FNO)建立了逼近和学习保证。该分析基于以下前提:只要解算子允许稳定且精确的谱离散化,FNO就能高效逼近和学习它们。为形式化这一思想,我们引入了通过谱方法定义的演化算子类,并推导了这些类的FNO逼近界和多项式样本复杂度保证。对于具有多项式非线性的方程,学习率主要取决于输入空间的光滑性和物理域的维度。我们的结果一致地适用于广泛的耗散方程族,而非单个固定的PDE,特别适用于Navier-Stokes、Allen-Cahn和Cahn-Hilliard方程。对于具有非多项式光滑非线性的方程,我们证明多项式样本复杂度仍然成立,但此时学习率额外依赖于非线性项的光滑性和耗散强度。总体而言,我们将经典谱逼近理论与现代算子学习联系起来,并解释了FNO何时能高效学习非线性演化算子。

英文摘要:

We establish approximation and learning guarantees for Fourier neural operators (FNOs) applied to time-$T$ solution operators of dissipative evolution equations. The analysis builds on the premise that FNOs can efficiently approximate and learn solution operators whenever these operators admit stable and accurate spectral discretizations. To formalize this idea, we introduce classes of evolution operators defined through spectral methods and derive FNO approximation bounds and polynomial sample complexity guarantees for these classes. For equations with polynomial nonlinearities, the learning rates depend primarily on the smoothness of the input space and the dimension of the physical domain. Our results hold uniformly over broad families of dissipative equations, rather than for a single fixed PDE, and apply in particular to the Navier--Stokes, Allen--Cahn, and Cahn--Hilliard equations. For equations with non-polynomial smooth nonlinearities, we prove that polynomial sample complexity still holds with rates that now additionally depend on the smoothness of the nonlinear terms and the dissipation strength. Overall, we connect classical spectral approximation theory with modern operator learning and explain when FNOs can learn nonlinear evolution operators efficiently.

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。

↑