Joint Neural Posterior Estimation and Model Selection for Chemical Reaction Networks

stat.ML, cs.LG, physics.chem-ph

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 40 pages total (11 pages main text, 29 pages appendix), 18 figures. Code available at: https://github.com/Esquivel-Arturo/JNPE

Code: https://github.com/Esquivel-Arturo/JNPE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Simulation-based inference using splitting schemes for partially observed diffusions in chemical reaction networks
• BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Python
• Validating Bayesian Inference Algorithms with Simulation-Based Calibration

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier