A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning

arXiv:2605.26341v2 Announce Type: replace Abstract: Physics-informed machine learning (PIML) integrates mechanistic knowledge, typically through partial differential equations (PDEs), into data-driven models. Despite strong empirical performance, its statistical generalisation properties remain poorly understood, especially for regression with unbounded losses. We develop a PAC-Bayesian framework for PIML that provides high-probability generalisation guarantees under potentially unbounded losses. Exploiting the structure of physics-informed objectives, we derive component-wise bounds whose complexity scales with the input-gradient energy of each loss, establishing a direct link between physical regularity and generalisation. We further introduce a PAC-Bayesian calibration procedure that yields computable gradient-based complexities while controlling rare large-gradient events through a residual-tail correction. Adopting a multi-task view of data fidelity, PDE residuals, initial conditions, and boundary conditions, we obtain a refined certificate with a single PAC-Bayesian complexity penalty, avoiding the looseness of independently bounding each component. Building on this certificate, we propose a bound-aware learning procedure that promotes empirical accuracy, proximity to a physics-informed prior, and low input-gradient complexity. Experiments on six PDE benchmarks yield substantially tighter certificates than bounded-loss and sub-Gaussian alternatives, while ablations quantify the effects of posterior-training data, calibration data, gradient envelopes, and hypothesis localisation.

Abstract:Physics-informed machine learning (PIML) integrates mechanistic knowledge, typically through partial differential equations (PDEs), into data-driven models. Despite strong empirical performance, its statistical generalisation properties remain poorly understood, especially for regression with unbounded losses. We develop a PAC-Bayesian framework for PIML that provides high-probability generalisation guarantees under potentially unbounded losses. Exploiting the structure of physics-informed objectives, we derive component-wise bounds whose complexity scales with the input-gradient energy of each loss, establishing a direct link between physical regularity and generalisation. We further introduce a PAC-Bayesian calibration procedure that yields computable gradient-based complexities while controlling rare large-gradient events through a residual-tail correction. Adopting a multi-task view of data fidelity, PDE residuals, initial conditions, and boundary conditions, we obtain a refined certificate with a single PAC-Bayesian complexity penalty, avoiding the looseness of independently bounding each component. Building on this certificate, we propose a bound-aware learning procedure that promotes empirical accuracy, proximity to a physics-informed prior, and low input-gradient complexity. Experiments on six PDE benchmarks yield substantially tighter certificates than bounded-loss and sub-Gaussian alternatives, while ablations quantify the effects of posterior-training data, calibration data, gradient envelopes, and hypothesis localisation.

Machine Learning (cs.LG); Machine Learning (stat.ML)

arXiv:2605.26341 [cs.LG]

(or arXiv:2605.26341v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.26341 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.

aiqbench analysis

A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning

Related coverage