2023/02/17 by Paul Escapil‐Inchauspé, Escapil-Inchauspé, Paul, Gonzalo A. Ruz +1 · 2 citations
Computer Science · Engineering · Physics and Astronomy · #Advancements in Semiconductor Devices and Circuit Design #Artificial Intelligence (cs.AI) #Computational Engineering #FOS: Computer and information sciences #Finance #Model Reduction and Neural Networks #Neural Networks and Applications #and Science (cs.CE)
paper · pdf · doi:10.48550/arxiv.2302.08835
openalex publication_date 2023/02/17 · openalex created_date 2023/02/23 · openalex updated_date 2026/07/29
We explore the data-parallel acceleration of physics-informed machine learning (PIML) schemes, with a focus on physics-informed neural networks (PINNs) for multiple graphics processing units (GPUs) architectures. In order to develop scale-robust and high-throughput PIML models for sophisticated applications which may require a large number of training points (e.g., involving complex and high-dimensional domains, non-linear operators or multi-physics), we detail a novel protocol based on h-analysis and data-parallel acceleration through the Horovod training framework. The protocol is backed by new convergence bounds for the generalization error and the train-test gap. We show that the acceleration is straightforward to implement, does not compromise training, and proves to be highly efficient and controllable, paving the way towards generic scale-robust PIML. Extensive numerical experiments with increasing complexity illustrate its robustness and consistency, offering a wide range of possibilities for real-world simulations.