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 2401.10490cs.LG
收藏

具有泛化误差保证的、基于自编码器的算子学习非线性模型降维

Generalization Error Guaranteed Auto-Encoder-Based Nonlinear Model Reduction for Operator Learning

Hong Kong Baptist University(香港浸会大学);Purdue University(普渡大学)

Hao Liu, Biraj Dahal, Rongjie Lai, Wenjing Liao

AI总结:

提出基于自编码器神经网络AENet的非线性模型降维方法以学习算子,通过非线性PDE实验验证其精度,并建立泛化误差理论,揭示样本复杂度与内蕴维度的关系及抗噪性。

摘要:

科学与工程中的许多物理过程自然地表示为无限维函数空间之间的算子。在此背景下,算子学习问题旨在从经验数据中提取这些物理过程,而由于数据的无限维或高维特性,这一任务颇具挑战。应对该挑战的一个核心组成部分是模型降维,它同时降低数据维度和问题规模。本文通过研究基于自编码器的神经网络(Auto-Encoder-based Neural Network,AENet),在模型降维中利用低维非线性结构。AENet首先学习输入数据的潜变量,然后学习从这些潜变量到相应输出数据的变换。数值实验验证了AENet能够准确学习非线性偏微分方程的解算子。此外,我们建立了一套数学与统计估计理论,用于分析AENet的泛化误差。理论框架表明,训练AENet的样本复杂度与所建模过程的内蕴维度密切相关,同时也证明了AENet对噪声具有显著的鲁棒性。

英文摘要:

Many physical processes in science and engineering are naturally represented by operators between infinite-dimensional function spaces. The problem of operator learning, in this context, seeks to extract these physical processes from empirical data, which is challenging due to the infinite or high dimensionality of data. An integral component in addressing this challenge is model reduction, which reduces both the data dimensionality and problem size. In this paper, we utilize low-dimensional nonlinear structures in model reduction by investigating Auto-Encoder-based Neural Network (AENet). AENet first learns the latent variables of the input data and then learns the transformation from these latent variables to corresponding output data. Our numerical experiments validate the ability of AENet to accurately learn the solution operator of nonlinear partial differential equations. Furthermore, we establish a mathematical and statistical estimation theory that analyzes the generalization error of AENet. Our theoretical framework shows that the sample complexity of training AENet is intricately tied to the intrinsic dimension of the modeled process, while also demonstrating the remarkable resilience of AENet to noise.

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。

↑