YoVDO

On the Use of Linear Surrogate Models for Bayesian Inverse Problems

Offered By: Society for Industrial and Applied Mathematics via YouTube

Tags

SIAM (Society for Industrial and Applied Mathematics) Courses Partial Differential Equations Courses

Course Description

Overview

Explore the use of linear surrogate models in solving Bayesian inverse problems during this one-hour virtual seminar presented by the Society for Industrial and Applied Mathematics. Delve into high-dimensional problems arising from the discretization of partial differential equations across various applications. Learn about the Bayesian approach to account for model discrepancy and discover a surprising result regarding the invariance of approximate posteriors when using linear surrogates. Examine case studies in corrosion detection, scattering, and electrical impedance tomography. Gain insights from speaker Ru Nicholson of the University of Auckland as part of the 42nd Imaging & Inverse Problems (IMAGINE) OneWorld SIAM-IS Virtual Seminar Series.

Syllabus

Introduction
Overview
Motivation
Bayesian Inverse Problems
Additive Error Model
Inference Problem
Bayesian approximation error approach
Corrosion detection
The likelihood
Examples
Scattering Case
EIT Samples
Conclusion


Taught by

Society for Industrial and Applied Mathematics

Related Courses

Differential Equations in Action
Udacity
Dynamical Modeling Methods for Systems Biology
Icahn School of Medicine at Mount Sinai via Coursera
An Introduction to Functional Analysis
École Centrale Paris via Coursera
Practical Numerical Methods with Python
George Washington University via Independent
The Finite Element Method for Problems in Physics
University of Michigan via Coursera