aiqbench analysis
This research addresses a critical blind spot in Physics-Informed Neural Networks (PINNs) by demonstrating that low training loss can mask incorrect physical parameters. The authors derive a closed-form audit method to estimate these coefficients directly from the frozen network, quantifying how well the model satisfies its governing equation to predict recovery accuracy. This work provides essential diagnostic tools for deploying PINNs in scientific computing where parameter fidelity is paramount.
Parameter misspecification in physics-informed neural networks: A closed-form audit and its limits
arXiv:2610.23948v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) are trained to minimize the residual of a prescribed equation, so a low training loss does not indicate whether a coefficient in that equation was specified incorrectly. This study evaluates what can be inferred about the encoded parameter from the trained network alone. When the residual is linear in the parameter, written as $A - \nu B$, the least-squares estimate $\hat{\nu} = A^{\top}B/B^{\top}B$ is obtained from a single evaluation of the frozen network, without retraining or reference data. Its accuracy depends on how closely the network satisfies its own equation, quantified by a normalized residual $\rho$. Recovery error is associated with $\rho$ (log-log correlation 0.72 across 36 convection-diffusion networks), and empirical exponents of 0.63 to 1.20 across three equations decompose into one half plus a measurable angular term. For Burgers' equation, a single-model test based on a block-bootstrap standard error flagged 3 of 300 correctly specified networks (observed false-alarm rate 1%), all 2% misspecifications at a practical budget, and two thirds of 1% misspecifications after convergence. For the self-similar blowup rate of the C\'ordoba-C\'ordoba-Fontelos equation, where the rate also enters the architecture, the estimator recovers about half of the misspecification, whereas $\rho$ increases approximately quadratically and distinguishes a 0.2% error. When the incorrect rate enters both the equation and the architecture, errors of up to 2% were not detected at the precision reached. At practical budgets, the raw loss can be lower for the misspecified model, a scaling effect that $\rho$ does not share.
Abstract:Physics-informed neural networks (PINNs) are trained to minimize the residual of a prescribed equation, so a low training loss does not indicate whether a coefficient in that equation was specified incorrectly. This study evaluates what can be inferred about the encoded parameter from the trained network alone. When the residual is linear in the parameter, written as $A - \nu B$, the least-squares estimate $\hat{\nu} = A^{\top}B/B^{\top}B$ is obtained from a single evaluation of the frozen network, without retraining or reference data. Its accuracy depends on how closely the network satisfies its own equation, quantified by a normalized residual $\rho$. Recovery error is associated with $\rho$ (log-log correlation 0.72 across 36 convection-diffusion networks), and empirical exponents of 0.63 to 1.20 across three equations decompose into one half plus a measurable angular term. For Burgers' equation, a single-model test based on a block-bootstrap standard error flagged 3 of 300 correctly specified networks (observed false-alarm rate 1%), all 2% misspecifications at a practical budget, and two thirds of 1% misspecifications after convergence. For the self-similar blowup rate of the Córdoba-Córdoba-Fontelos equation, where the rate also enters the architecture, the estimator recovers about half of the misspecification, whereas $\rho$ increases approximately quadratically and distinguishes a 0.2% error. When the incorrect rate enters both the equation and the architecture, errors of up to 2% were not detected at the precision reached. At practical budgets, the raw loss can be lower for the misspecified model, a scaling effect that $\rho$ does not share.
Machine Learning (cs.LG); Numerical Analysis (math.NA); Computational Physics (physics.comp-ph)
I.2.6; G.1.8; G.1.3
arXiv:2610.23948 [cs.LG]
(or arXiv:2610.23948v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.23948 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 349 words