arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.18210cs.LGstat.ML
收藏

算子代理模型

Operator Surrogates

ETH Zürich(苏黎世联邦理工学院);Uni Heidelberg(海德堡大学);SAM(应用数学与力学研究所);IWR(计算机科学研究中心)

Christoph Schwab, Josephine Westermann, Jakob Zech

AI总结:

本章介绍算子代理模型的数学基础,涵盖其构建范式、各类表示系统与代理架构,分析逼近与泛化误差理论,探讨克服维度诅咒的方法及收敛率界,为相关研究提供文献指引。

摘要:

本章对算子代理模型进行数学介绍,这类模型是有限参数映射,用于逼近无穷维(函数)空间之间的复杂(通常为非线性)算子。构建算子代理模型的典型方法是编码器-逼近器-解码器范式,该范式将无穷维输入映射到有限维潜空间,经处理后再映射回无穷维输出空间。我们讨论了多种创建高效表示系统的方法,包括Banach框架等稳定线性框架,以及主成分分析(PCA)、活性子空间、非线性自编码器等数据驱动技术。随后,我们综述了关键的代理架构,对比了基于多项式混沌展开及相关技术的谱方法与更新的神经网络方法。我们还探讨了不依赖表示系统的架构,如傅里叶神经算子和Transformer,详细阐述了它们之间的关系,以及与其他神经网络算子代理模型(尤其是通过所谓“算法展开”得到的模型)的关联。此外,我们介绍了逼近误差与泛化误差的理论分析,解释了全纯性等提供的潜在低维结构对克服所谓“维度诅咒”的重要性——“维度诅咒”指数值算法的复杂度往往随问题维度呈指数增长。我们给出了依赖于可训练参数数量及输入输出数据正则性的全纯算子的收敛率界。全文以直观性优先于详细技术证明,并为详细论证提供了精确的文献指引。

英文摘要:

This chapter provides a mathematical introduction to operator surrogates, which are finite-parametric maps approximating complex (typically nonlinear) operators between infinite-dimensional (function) spaces. A typical approach to constructing operator surrogates is the encoder-approximator-decoder paradigm, whereby infinite-dimensional inputs are mapped to a finite-dimensional latent space, processed, and then mapped back to the infinite-dimensional output space. We discuss various methods for creating efficient representation systems, including stable linear frameworks like Banach frames and data-driven techniques such as Principal Component Analysis (PCA), Active Subspaces, and nonlinear autoencoders. Subsequently, we survey key surrogate architectures, contrasting spectral methods, based on polynomial chaos expansions and related technologies, with more recent neural network approaches. We further discuss architectures that do not rely on representation systems, such as Fourier Neural Operators and transformers. We elaborate on their relationship and how they relate to other neural network operator surrogates, particularly those obtained by so-called "algorithm-unrolling". Additionally, we provide an introduction to the theoretical analysis of approximation and generalization errors. We explain how underlying low-dimensional structures, provided for example by holomorphy, are essential to overcome the so-called "curse of dimensionality": this refers to the fact that the complexity of numerical algorithms tends to increase exponentially in the problem dimensionality. We present convergence rate bounds for holomorphic operators that depend on the number of trainable parameters and the regularity of the input and output data. Throughout, we prioritize intuition over detailed technical proofs and provide precise pointers to the literature for detailed arguments.

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。

↑