Online Program Home
My Program

Abstract Details

Activity Number:
265 - Section on Bayesian StaSection on Statistical Educationtistical Science A.M. Roundtable Discussion (Added Fee)
Type: Roundtables
Date/Time: Tuesday, July 31, 2018 : 7:00 AM to 8:15 AM
Sponsor: Section on Bayesian Statistical Science
Abstract #330208
Title: Interpretable Statistical Machine Learning for Validation and Uncertainty Quantification of Complex Models
Author(s): Ana Kupresanin*
Companies: Lawrence Livermore National Laboratory
Keywords: Bayesian hierarchical model; Uncertainty quantification; Interpretable ML

Advances in high performance computing have enabled detailed simulations of real world physical processes, and these simulations produce large datasets. Even as detailed as they are, these simulations are only approximations of imperfect mathematical models, and furthermore, their outputs depend on inputs that are themselves uncertain. The main goal of a validation and uncertainty quantification methodology is to determine the uncertainty, that is, the relationship between the true value of a quantity of interest and its prediction by the simulation. A principled approach to building hierarchical models, even relatively shallow, but informed by the available understanding of physics and statistics is a required step towards useful and rigorous uncertainty quantification of complex physics-based models, and addresses three main concerns: interpretability, probabilistic rigor and bounding of false discovery.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program