DeepAI AI Chat
Log In Sign Up

Least squares approximations in linear statistical inverse learning problems

by   Tapio Helin, et al.

Statistical inverse learning aims at recovering an unknown function f from randomly scattered and possibly noisy point evaluations of another function g, connected to f via an ill-posed mathematical model. In this paper we blend statistical inverse learning theory with the classical regularization strategy of applying finite-dimensional projections. Our key finding is that coupling the number of random point evaluations with the choice of projection dimension, one can derive probabilistic convergence rates for the reconstruction error of the maximum likelihood (ML) estimator. Convergence rates in expectation are derived with a ML estimator complemented with a norm-based cut-off operation. Moreover, we prove that the obtained rates are minimax optimal.


page 1

page 2

page 3

page 4


Convex regularization in statistical inverse learning problems

We consider a statistical inverse learning problem, where the task is to...

Tikhonov regularization with oversmoothing penalty for nonlinear statistical inverse problems

In this paper, we consider the nonlinear ill-posed inverse problem with ...

Convergence analysis of Tikhonov regularization for non-linear statistical inverse learning problems

We study a non-linear statistical inverse learning problem, where we obs...

Optimal Rates For Regularization Of Statistical Inverse Learning Problems

We consider a statistical inverse learning problem, where we observe the...

Shearlet-based regularization in statistical inverse learning with an application to X-ray tomography

Statistical inverse learning theory, a field that lies at the intersecti...

A statistical physics approach to learning curves for the Inverse Ising problem

Using methods of statistical physics, we analyse the error of learning c...

Convergence Rates for Learning Linear Operators from Noisy Data

We study the Bayesian inverse problem of learning a linear operator on a...