skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Elliptic PDE learning is provably data-efficient
Partial differential equations (PDE) learning is an emerging field that combines physics and machine learning to recover unknown physical systems from experimental data. While deep learning models traditionally require copious amounts of training data, recent PDE learning techniques achieve spectacular results with limited data availability. Still, these results are empirical. Our work provides theoretical guarantees on the number of input–output training pairs required in PDE learning. Specifically, we exploit randomized numerical linear algebra and PDE theory to derive a provably data-efficient algorithm that recovers solution operators of three-dimensional uniformly elliptic PDEs from input–output data and achieves an exponential convergence rate of the error with respect to the size of the training dataset with an exceptionally high probability of success.  more » « less
Award ID(s):
2045646
PAR ID:
10508645
Author(s) / Creator(s):
; ;
Publisher / Repository:
PNAS
Date Published:
Journal Name:
Proceedings of the National Academy of Sciences
Volume:
120
Issue:
39
ISSN:
0027-8424
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, IFAC-PapersOnLine)
    Recently, a broad class of linear delayed and ODE-PDEs systems was shown to have an equivalent representation using Partial Integral Equations (PIEs). In this paper, we use this PIE representation, combined with algorithms for convex optimization of Partial Integral (PI) operators to bound the H2-norm for input-output systems of this class. Specifically, the methods proposed here apply to delayed and ODE-PDE systems (including delayed PDE systems) in one or two spatial variables where the disturbance does not enter through the boundary. For such systems, we define a notion of H2-norm using an initial state-to-output framework and show that this notion reduces to more traditional concepts under the assumption of existence of a strongly continuous semigroup. Next, we consider input-output systems for which there exists a PIE representation and for such systems show that computing a minimal upper bound on the H2-norm of delayed and PDE systems can be equivalently formulated as a convex optimization problem subject to linear PI operator inequalities (LPIs). We convert, then, these optimization problems to Semi-Definite Programming (SDP) problems using the PIETOOLS toolbox. Finally, we apply the results to several numerical examples – focusing on time-delay systems (TDS) for which comparable H2 approximation results are available in the literature. The numerical results demonstrate the accuracy of the computed upper bound on the H2-norm. 
    more » « less
  2. ; (, Researchgate/Digital Commons/Github)
    Included in this dataset are: 1. Monte Carlo (MC) simulation data used for PDE identification 2. Molecular dynamics (MD) simulation data used for PDE identification 3. LAMMPS input file for PDE validation, Case 1: linear initial C profile 4. LAMMPS input file for PDE validation, Case 2: exponential initial C profile They are used in our manuscript, Learning the Governing PDE of Solid Diffusion from Atomistic Simulations, by Wongelemengist Nadew and Haoran Wang 
    more » « less
  3. ; ; (, Earthquake Engineering & Structural Dynamics)
    Abstract We introduce a novel data‐informed convolutional neural network (CNN) approach that utilizes sparse ground motion measurements to accurately identify effective seismic forces in a truncated two‐dimensional (2D) domain. Namely, this paper presents the first prototype of a CNN capable of inferring domain reduction method (DRM) forces, equivalent to incident waves, across all nodes in the DRM layer. It achieves this from sparse measurement data in a multidimensional setting, even in the presence of incoherent incident waves. The method is applied to shear (SH) waves propagating into a domain truncated by a wave‐absorbing boundary condition (WABC). By effectively training the CNN using input‐layer features (surface sensor measurements) and output‐layer features (effective forces at a DRM layer), we achieve significant reductions in processing time compared to PDE‐constrained optimization methods. The numerical experiments demonstrate the method's effectiveness and robustness in identifying effective forces, equivalent to incoherent incident waves, at a DRM layer. 
    more » « less
  4. ; ; (, Proceedings of the International Conference on Machine Learning)
    Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We develop a notion of representation vulnerability that captures the maximum change of mutual information between the input and output distributions, under the worst-case input perturbation. Then, we prove a theorem that establishes a lower bound on the minimum adversarial risk that can be achieved for any downstream classifier based on its representation vulnerability. We propose an unsupervised learning method for obtaining intrinsically robust representations by maximizing the worst-case mutual information between the input and output distributions. Experiments on downstream classification tasks support the robustness of the representations found using unsupervised learning with our training principle. 
    more » « less
  5. ; ; ; ; ; ; (, Machine Learning: Science and Technology)
    Abstract In this paper, we aim to explore novel machine learning (ML) techniques to facilitate and accelerate the construction of universal equation-Of-State (EOS) models with a high accuracy while ensuring important thermodynamic consistency. When applying ML to fit a universal EOS model, there are two key requirements: (1) a high prediction accuracy to ensure precise estimation of relevant physics properties and (2) physical interpretability to support important physics-related downstream applications. We first identify a set of fundamental challenges from the accuracy perspective, including an extremely wide range of input/output space and highly sparse training data. We demonstrate that while a neural network (NN) model may fit the EOS data well, the black-box nature makes it difficult to provide physically interpretable results, leading to weak accountability of prediction results outside the training range and lack of guarantee to meet important thermodynamic consistency constraints. To this end, we propose a principled deep regression model that can be trained following a meta-learning style to predict the desired quantities with a high accuracy using scarce training data. We further introduce a uniquely designed kernel-based regularizer for accurate uncertainty quantification. An ensemble technique is leveraged to battle model overfitting with improved prediction stability. Auto-differentiation is conducted to verify that necessary thermodynamic consistency conditions are maintained. Our evaluation results show an excellent fit of the EOS table and the predicted values are ready to use for important physics-related tasks. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email