{"ID":2825881,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20447","arxiv_id":"2512.20447","title":"Neural Scaling Laws for Learning-based Identification of Nonlinear Systems","abstract":"The use of machine learning models in system identification has increased due to their ability to approximate complex nonlinear dynamics with high accuracy. However, often it is not clear how the performance of trained models scales with given resources such as data, compute, and model size. To allow for a better understanding of the scalability of the performance of machine learning models, we verify neural scaling laws (NSLs) in the context of system identification from input-state-output data using different evaluation metrics for accuracy and different system architectures, including input-affine and physics-informed port-Hamiltonian representations. Our verified NSLs can help to forecast performance improvements and guide model design or data acquisition.","short_abstract":"The use of machine learning models in system identification has increased due to their ability to approximate complex nonlinear dynamics with high accuracy. However, often it is not clear how the performance of trained models scales with given resources such as data, compute, and model size. To allow for a better under...","url_abs":"https://arxiv.org/abs/2512.20447","url_pdf":"https://arxiv.org/pdf/2512.20447v2","authors":"[\"Marco Roschkowski\",\"Karim Cherifi\",\"Hannes Gernandt\"]","published":"2025-12-23T15:39:24Z","proceeding":"math.OC","tasks":"[\"math.OC\"]","methods":"[]","has_code":false}