A PAC-Bayesian framework for PIML is developed that provides high-probability generalisation guarantees under potentially unbounded losses, and a bound-aware learning procedure is proposed that promotes empirical accuracy, proximity to a physics-informed prior, and low input-gradient complexity.
Thi-Trang Nguyen, Amaury Habrard, Benjamin Guedj· arXiv.org· 0 citations
A derandomization framework for stochastic majority votes is proposed that derives two families of high-probability generalization bounds, covering both data-independent and data-dependent constructions of the ensemble, which naturally lead to a self-bounding learning algorithm optimizing deterministic majority vote gu...
J. Bastian, Benjamin Leblanc, Pascal Germain et al.· 0 citations
It is argued that this paper is intended both for ML experts who design new PDE discovery algorithms and for users of these methods aiming, in real applications, to discover and validate well-founded scientific laws.