Liverani L, Steynberg M, Zuazua Iriondo E (2025)
Publication Language: English
Publication Status: Submitted
Publication Type: Unpublished / Preprint
Future Publication Type: Journal article
Publication year: 2025
Open Access Link: https://arxiv.org/abs/2509.14123v1
We present Hybrid-Cooperative Learning (HYCO), a hybrid modeling framework that iteratively integrates physics-based and data-driven models through a mutual regularization mech- anism. Unlike traditional approaches that impose physical constraints directly on synthetic models, HYCO treats the physical and synthetic components as co-trained agents: the physical and syn- thetic models are nudged toward agreement, while the synthetic model is enhanced to better fit the available data. This cooperative learning scheme is naturally parallelizable and improves robust- ness to noise as well as to sparse or heterogeneous data. Extensive numerical experiments on both static and time-dependent problems demonstrate that HYCO outperforms classical physics-based and data-driven methods, recovering accurate solutions and model parameters even under ill-posed conditions. The method also admits a natural game-theoretic interpretation, enabling alternating optimization and paving the way for future theoretical developments.
APA:
Liverani, L., Steynberg, M., & Zuazua Iriondo, E. (2025). HYCO: Hybrid-Cooperative Learning for Data-Driven PDE Modeling. (Unpublished, Submitted).
MLA:
Liverani, Lorenzo, Matthys Steynberg, and Enrique Zuazua Iriondo. HYCO: Hybrid-Cooperative Learning for Data-Driven PDE Modeling. Unpublished, Submitted. 2025.
BibTeX: Download