Discretization Error Analysis for Tikhonov Regularization
in Learning Theory ## AbstractWe study the connections between learning from examples and inverse problems. We show that learning from examples can be seen as the discretization of a stochastic inverse problem defined by a Carleman operator. In particular we develop a discretization strategy for this class of inverse problems and we give a convergence analysis. Our approach can be applied to other classes of problems such as integral equations.
[Edit] |