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.
A Unified DeepONet Framework for Logarithmically Stable Infinite-Dimensional Inverse Problems
School of Mathematics and Shing-Tung Yau Center, Southeast University(东南大学数学系及施一公中心);Shanghai Institute for Mathematics and Interdisciplinary Sciences (SIMIS)(上海数学与交叉学科研究院)
Two-Step MV-DeepONet: Probabilistic Operator Learning for Uncertainty Propagation Driven by Random Input Fields
School of Mathematics and Physics, North China Electric Power University(华北电力大学数理学院);School of Energy Power and Mechanical Engineering, North China Electric Power University(华北电力大学能源动力与机械工程学院)
Towards Size-Independent Generalization Bounds for Deep Operator Nets
Indian Institute of Technology Kanpur (IIT Kanpur)(印度理工学院坎普尔分校(IIT坎普尔));University of Michigan(密歇根大学);University of Florida(佛罗里达大学);The University of Manchester(曼彻斯特大学)
Stanford University(斯坦福大学);University of Maryland at College Park(马里兰大学帕克分校);Eindhoven University of Technology(埃因霍温理工大学);Oden Institute for Computational Engineering and Sciences, University of Texas at Austin(德克萨斯大学奥斯汀分校奥登计算工程与科学研究所);University of Southern California(南加州大学)
Neural-POD: A Plug-and-Play Neural Operator Framework for Infinite-Dimensional Functional Nonlinear Proper Orthogonal Decomposition
Department of Mathematics and Statistics(数学与统计学系);Utah State University(犹他州立大学);School of Electrical and Computer Engineering(电气与计算机工程学院);Purdue University(普渡大学);Department of Mathematics(数学系);School of Mechanical Engineering(机械工程学院)
Neural-POD通过在函数空间中学习非线性正交基函数,提供了一种可集成到降阶模型和算子学习框架中的通用表示模块,用于提升AI for science的泛化能力和可解释性。
A class of high-order discontinuous-Galerkin methods satisfying infinitely many entropy conditions with provable error estimates and strong convergence for general nonlinear conservation laws
Stability and Discretization Error of State Space Model Neural Operators
École polytechnique(巴黎政治经济学院);Université Claude Bernard Lyon 1(里昂1大学);CNRS(法国国家科学研究中心);LAGEPP UMR 5007;Université Lyon 1(里昂1大学);INSA Lyon(里昂国立应用科学学院);LIRIS(里昂图像与信号研究所)