Practical multi-fidelity machine learning: Fusion of deterministic and Bayesian models
Published in Computational Mechanics, 2026
Multi-fidelity machine learning methods address the accuracy-efficiency trade-off by integrating scarce, resource-intensive high-fidelity data with abundant but less accurate low-fidelity data. This work proposes a practical strategy that combines a deterministic low-fidelity model, transfer learning, and a Bayesian residual model to provide predictions with uncertainty quantification.
Recommended citation: Yi, J., Cheng, J., & Bessa, M. A. (2026). Practical multi-fidelity machine learning: Fusion of deterministic and Bayesian models. Computational Mechanics.
Download Paper | Download Bibtex