DeepAI
Log In Sign Up

Continuum Limit of Posteriors in Graph Bayesian Inverse Problems

06/22/2017
by   Nicolas Garcia Trillos, et al.
0

We consider the problem of recovering a function input of a differential equation formulated on an unknown domain M. We assume to have access to a discrete domain M_n={x_1, ..., x_n}⊂ M, and to noisy measurements of the output solution at p< n of those points. We introduce a graph-based Bayesian inverse problem, and show that the graph-posterior measures over functions in M_n converge, in the large n limit, to a posterior over functions in M that solves a Bayesian inverse problem with known domain. The proofs rely on the variational formulation of the Bayesian update, and on a new topology for the study of convergence of measures over functions on point clouds to a measure over functions on the continuum. Our framework, techniques, and results may serve to lay the foundations of robust uncertainty quantification of graph-based tasks in machine learning. The ideas are presented in the concrete setting of recovering the initial condition of the heat equation on an unknown manifold.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/24/2021

Consistency of Bayesian inference with Gaussian process priors for a parabolic inverse problem

We consider the statistical nonlinear inverse problem of recovering the ...
01/14/2021

All-at-once formulation meets the Bayesian approach: A study of two prototypical linear inverse problems

In this work, the Bayesian approach to inverse problems is formulated in...
10/16/2019

Consistency of Bayesian inference with Gaussian process priors in an elliptic inverse problem

For O a bounded domain in R^d and a given smooth function g:O→R, we cons...
06/17/2022

Learning the parameters of a differential equation from its trajectory via the adjoint equation

The paper contributes to strengthening the relation between machine lear...
02/18/2020

Stabilities of Shape Identification Inverse Problems in a Bayesian Framework

A general shape identification inverse problem is studied in a Bayesian ...
09/13/2018

On Bayesian Consistency for Flows Observed Through a Passive Scalar

We consider the statistical inverse problem of estimating a background f...
03/23/2020

Inverse heat source problem and experimental design for determining iron loss distribution

Iron loss determination in the magnetic core of an electrical machine, s...