A Learning Theory in Linear Systems under Compositional Models

06/29/2018
by   Se Un Park, et al.
0

We present a learning theory for the training of a linear system operator having an input compositional variable and propose a Bayesian inversion method for inferring the unknown variable from an output of a noisy linear system. We assume that we have partial or even no knowledge of the operator but have training data of input and ouput. A compositional variable satisfies the constraints that the elements of the variable are all non-negative and sum to unity. We quantified the uncertainty in the trained operator and present the convergence rates of training in explicit forms for several interesting cases under stochastic compositional models. The trained linear operator with the covariance matrix, estimated from the training set of pairs of ground-truth input and noisy output data, is further used in evaluation of posterior uncertainty of the solution. This posterior uncertainty clearly demonstrates uncertainty propagation from noisy training data and addresses possible mismatch between the true operator and the estimated one in the final solution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/26/2021

Compositional Game Theory, Compositionally

We present a new compositional approach to compositional game theory (CG...
research
06/09/2018

Well-posedness conditions in stochastic inversion problems

Stochastic inversion problems arise when it is wanted to estimate the pr...
research
08/27/2021

Convergence Rates for Learning Linear Operators from Noisy Data

We study the Bayesian inverse problem of learning a linear operator on a...
research
01/24/2020

Estimation for Compositional Data using Measurements from Nonlinear Systems using Artificial Neural Networks

Our objective is to estimate the unknown compositional input from its ou...
research
10/19/2020

Operator Augmentation for Noisy Elliptic Systems

In the computational sciences, one must often estimate model parameters ...
research
04/05/2018

Density estimation on small datasets

How might a smooth probability distribution be estimated, with accuratel...

Please sign up or login with your details

Forgot password? Click here to reset