Log In Sign Up

Continuum Limit of Posteriors in Graph Bayesian Inverse Problems

by   Nicolas Garcia Trillos, et al.

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.


page 1

page 2

page 3

page 4


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

We consider the statistical nonlinear inverse problem of recovering the ...

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...

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...

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

The paper contributes to strengthening the relation between machine lear...

Stabilities of Shape Identification Inverse Problems in a Bayesian Framework

A general shape identification inverse problem is studied in a Bayesian ...

On Bayesian Consistency for Flows Observed Through a Passive Scalar

We consider the statistical inverse problem of estimating a background f...

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

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