Logo image
Back
On the discrepancy principle and generalised maximum likelihood for regularisation
Journal article   Peer reviewed

On the discrepancy principle and generalised maximum likelihood for regularisation

M.A. Lukas
Bulletin of the Australian Mathematical Society, Vol.52(3), pp.399-424
1995
DOI: https://doi.org/10.1017/S0004972700014891
url
Link to Published Version *Subscription may be requiredView

Abstract

Let fnλ be the regularised solution of a general, linear operator equation, K f0 = g, from discrete, noisy data yi = g(xi ) + εi, i = 1, …, n, where εi are uncorrelated random errors with variance σ2. In this paper, we consider the two well–known methods – the discrepancy principle and generalised maximum likelihood (GML), for choosing the crucial regularisation parameter λ. We investigate the asymptotic properties as n → ∞ of the “expected” estimates λD and λM corresponding to these two methods respectively. It is shown that if f0 is sufficiently smooth, then λD is weakly asymptotically optimal (ao) with respect to the risk and an L2 norm on the output error. However, λD oversmooths for all sufficiently large n and also for all sufficiently small σ2. If f0 is not too smooth relative to the regularisation space W, then λD can also be weakly ao with respect to a whole class of loss functions involving stronger norms on the input error. For the GML method, we show that if f0 is smooth relative to W (for example f0 xs2208 Wθ, 2, θ > m, if W = Wm, 2), then λM is asymptotically sub-optimal and undersmoothing with respect to all of the loss functions above.

Details

Metrics

47 Record Views
10 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Citation topics
9 Mathematics
9.162 Numerical Methods
9.162.1492 Inverse Problems
Web Of Science research areas
Mathematics
ESI research areas
Mathematics
Logo image