.png){kind=icon}
Return
Normalizing flows for Bayesian parameter inference in computational mechanics
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2026.114263.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Normalizing Flows are explored for Bayesian parameter inference in computational mechanics. • Comparative benchmarks are performed against standard MCMC methods. • Posterior quality is assessed via KL divergence and L1 distance under equal computational budgets. • Normalizing Flows achieve accuracy comparable to MCMC. • Flow-based inference shows promise for scalable Bayesian inverse problems in engineering.
Keywords:
Normalizing Flows
Bayesian inference
Computational mechanics
Parameter estimation
Markov Chain Monte Carlo
Journal
IF:
8
Papers:
5.5K
Citations:
3.5W
Organization
No organization information available
Cited Papers
ShareSaveShareSaveShareSaveShareSave
Probabilistic model updating of civil structures with a decentralized variational inference approach
PREAI
ShareSaveThe Role of AI, Machine Learning, and Big Data in Digital Twinning: A Systematic Literature Review, Challenges, and Opportunities.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSave
View more