arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09618math.NAcs.NA
收藏

DeepOnets的误差估计:无限维深度学习框架

Error estimates for DeepOnets: A deep learning framework in infinite dimensions

Samuel Lanthaler, Siddhartha Mishra, George Em Karniadakis

摘要:

DeepONets最近被提出作为学习无限维巴拿赫空间之间映射的非线性算子的框架。我们分析了DeepONets,并证明了对所产生的近似和泛化误差的估计。特别地,我们扩展了DeepONets的普适逼近性质,以包括非紧空间中的可测映射。通过分解成编码,近似和重建误差的错误,我们证明了下和上界的总误差,它的协方差算子的谱衰减特性,与相关的措施。我们得到几乎最佳的误差界与非常一般的仿射重建和随机传感器的位置以及泛化误差的范围,使用覆盖数参数。我们说明了我们的一般框架与非线性算子的四个原型的例子,即那些出现在非线性强迫常微分方程,椭圆型偏微分方程与变系数和非线性抛物和双曲偏微分方程。虽然DeepONets对任意Lipschitz算子的近似精度$ε$被认为受到“维数灾难”的影响,(需要$1/ε$中指数大小的神经网络),相反,对于所有上述感兴趣的具体示例,我们严格证明DeepONets可以打破这种维数灾难(使用可以在$1/ε$中代数增长的大小的神经网络实现精确$ε$)。因此,我们证明了一个潜在的大类运营商与这个机器学习框架的有效近似。

英文摘要:

DeepONets have recently been proposed as a framework for learning nonlinear operators mapping between infinite dimensional Banach spaces. We analyze DeepONets and prove estimates on the resulting approximation and generalization errors. In particular, we extend the universal approximation property of DeepONets to include measurable mappings in non-compact spaces. By a decomposition of the error into encoding, approximation and reconstruction errors, we prove both lower and upper bounds on the total error, relating it to the spectral decay properties of the covariance operators, associated with the underlying measures. We derive almost optimal error bounds with very general affine reconstructors and with random sensor locations as well as bounds on the generalization error, using covering number arguments. We illustrate our general framework with four prototypical examples of nonlinear operators, namely those arising in a nonlinear forced ODE, an elliptic PDE with variable coefficients and nonlinear parabolic and hyperbolic PDEs. While the approximation of arbitrary Lipschitz operators by DeepONets to accuracy $ε$ is argued to suffer from a "curse of dimensionality" (requiring a neural networks of exponential size in $1/ε$), in contrast, for all the above concrete examples of interest, we rigorously prove that DeepONets can break this curse of dimensionality (achieving accuracy $ε$ with neural networks of size that can grow algebraically in $1/ε$). Thus, we demonstrate the efficient approximation of a potentially large class of operators with this machine learning framework.

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。

↑