Operator Learning for Hyperbolic PDEs

Authors: Christopher Wang, Alex Townsend

JMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also include numerical experiments which corroborate our theoretical findings. Keywords: Data-driven PDE learning, hyperbolic PDE, operator learning, low-rank approximation, randomized SVD. A numerical implementation and example of our algorithm is presented in Section 5. Finally, we summarize our results and discuss further directions of research in Section 6. Figure 6: Empirical rate of convergence of Algorithm 2.
Researcher Affiliation Academia Christopher Wang EMAIL Department of Mathematics Cornell University Ithaca, NY 14853, USA. Alex Townsend EMAIL Department of Mathematics Cornell University Ithaca, NY 14853, USA.
Pseudocode Yes Algorithm 1 Approximating F via r SVD. Algorithm 2 Learning the solution operator via input-output data. Algorithm 3 Detecting the numerical rank of F in a subdomain.
Open Source Code Yes MATLAB code is available at https://github.com/chriswang030/OperatorLearningforHPDEs.
Open Datasets No Input-output data was generated using the known analytical expression for the true Green s function. The paper does not provide concrete access information for a publicly available or open dataset.
Dataset Splits No The paper discusses
Hardware Specification No The paper does not provide specific hardware details for running the experiments. It generally refers to
Software Dependencies No We implement Algorithms 1, 2, and 3 in MATLAB for the constant coefficient wave operator Lu = utt 4uxx with homogeneous initial and boundary conditions. No specific version numbers are provided for MATLAB or any other software dependencies.
Experiment Setup No The paper mentions discretizing the domain