By Topic

On inverse problems with unknown operators

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Efromovich, S. ; Dept. of Math. & Stat., New Mexico Univ., Albuquerque, NM, USA ; Koltchinskii, V.

Consider a problem of recovery of a smooth function (signal, image) f∈ℱ∈L2([0, 1]d) passed through an unknown filter and then contaminated by a noise. A typical model discussed in the paper is described by a stochastic differential equation dYfε(t)=(Hf)(t)dt+εdW(t), t∈[0, 1]d, ε>0 where H is a linear operator modeling the filter and W is a Brownian motion (sheet) modeling a noise. The aim is to recover f with asymptotically (as ε→0) minimax mean integrated squared error. Traditionally, the problem is studied under the assumption that the operator H is known, then the ill-posedness of the problem is the main concern. In this paper, a more complicated and more realistic case is considered where the operator is unknown; instead, a training set of n pairs {(el, Y(el )σ), l=1, 2,…, n}, where {el} is an orthonormal system in L2 and {Y(el)σ} denote the solutions of stochastic differential equations of the above type with f=el and ε=σ is available. An optimal (in a minimax sense over considered operators and signals) data-driven recovery of the signal is suggested. The influence of ε, σ, and n on the recovery is thoroughly studied; in particular, we discuss an interesting case of a larger noise during the training and present formulas for threshold levels for n beyond which no improvement in recovery of input signals occurs. We also discuss the case where H is an unknown perturbation of a known operator. We describe a class of perturbations for which the accuracy of recovery of the signal is asymptotically the same (up to a constant) as in the case of precisely known operator

Published in:

Information Theory, IEEE Transactions on  (Volume:47 ,  Issue: 7 )