A Nonparametric Bayesian Solution of the Empirical Stochastic Inverse Problem
By: Haiyi Shi , Lei Yang , Jiarui Chi and more
Potential Business Impact:
Helps computers guess answers for tricky problems.
The stochastic inverse problem is a key ingredient in making inferences, predictions, and decisions for complex science and engineering systems. We formulate and analyze a nonparametric Bayesian solution for the stochastic inverse problem. Key properties of the solution are proved and the convergence and error of a computational solution obtained by random sampling is analyzed. Several applications illustrate the results.
Similar Papers
A Nonparametric Bayesian Solution of the Empirical Stochastic Inverse Problem
Methodology
Helps predict how things will work.
Optimal Estimation and Uncertainty Quantification for Stochastic Inverse Problems via Variational Bayesian Methods
Numerical Analysis
Finds hidden answers in messy data.
Solving Inverse Problems in Stochastic Self-Organising Systems through Invariant Representations
Adaptation and Self-Organizing Systems
Finds hidden rules behind messy patterns.