Skip to yearly menu bar Skip to main content


PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification

Qianli Shen · Wai Hoh Tang · Zhun Deng · Apostolos Psaros · Kenji Kawaguchi

Great Hall & Hall B1+B2 (level 1) #415


Standard approaches for uncertainty quantification in deep learning and physics-informed learning have persistent limitations. Indicatively, strong assumptions regarding the data likelihood are required, the performance highly depends on the selection of priors, and the posterior can be sampled only approximately, which leads to poor approximations because of the associated computational cost.This paper introduces and studies confidence interval (CI) estimation for deterministic partial differential equations as a novel problem.That is, to propagate confidence, in the form of CIs, from data locations to the entire domain with probabilistic guarantees.We propose a method, termed Physics-Informed Confidence Propagation (PICProp), based on bi-level optimization to compute a valid CI without making heavy assumptions.We provide a theorem regarding the validity of our method, and computational experiments, where the focus is on physics-informed learning. Code is available at

Chat is not available.