Empirical risk minimization in inverse problems: Extended technical version

Details Empirical risk minimization in inverse problems: Extended technical version Empirical risk minimization in inverse problems: Extended technical version

2009-04-20

arxiv.org/abs/0904.2977v1

Mathematics

Statistics Theory

Scientific paper

We study estimation of a multivariate function $f:{\bf R}^d \to {\bf R}$ when the observations are available from function $Af$, where $A$ is a known linear operator. Both the Gaussian white noise model and density estimation are studied. We define an $L_2$ empirical risk functional, which is used to define an $\delta$-net minimizer and a dense empirical risk minimizer. Upper bounds for the mean integrated squared error of the estimators are given. The upper bounds show how the difficulty of the estimation depends on the operator through the norm of the adjoint of the inverse of the operator, and on the underlying function class through the entropy of the class. Corresponding lower bounds are also derived. As examples we consider convolution operators and the Radon transform. In these examples the estimators achieve the optimal rates of convergence. Furthermore, a new type of oracle inequality is given for inverse problems in additive models.

Affiliated with

Also associated with

No associations

Rating

Empirical risk minimization in inverse problems: Extended technical version does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Empirical risk minimization in inverse problems: Extended technical version, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Empirical risk minimization in inverse problems: Extended technical version will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-173863