Related papers: Learning a regression function via Tikhonov regula…
This paper has been withdrawn by the author due to some mistakes
This paper has been withdrawn by the author. It will be replaced, substantially modified, by sections of the author's completed PhD thesis.
This paper has been withdrawn by the author(s), due to the existence of a much better paper in http://arxiv.org/abs/cs.CR/0207027
This paper has been withdrawn by the author due to a critical error in the proof of Theorem A pointed out by Burkhard Wilking.
In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues. Regularization is known to be effective in such…
This paper has been withdrawn.
This paper has been withdrawn by the author, due to possible counter-examples.
The paper has been withdrawn by change of content and some errors in the examples.
There is a conceptual error in the main argument of this paper (essentially a regularization scheme is changed in the middle of a calculation), and therefore it is withdrawn. Interested readers are instead referred to hep-th/9811137.
This paper has been withdrawn since the results are not satisfied.
The paper was removed.
We study inverse problems F(f) = g with perturbed right hand side g^{obs} corrupted by so-called impulsive noise, i.e. noise which is concentrated on a small subset of the domain of definition of g. It is well known that Tikhonov-type…
This paper studies a machine learning regression problem as a multivariate approximation problem using the framework of the theory of random functions. An ab initio derivation of a regression method is proposed, starting from postulates of…
We present a new approach to convexification of the Tikhonov regularization using a continuation method strategy. We embed the original minimization problem into a one-parameter family of minimization problems. Both the penalty term and the…
This article has been withdrawn due to an error in a proof of the main result.
This paper has been withdrawn.
This paper has been withdrawn by the authors due to errors in the X-ray diffraction data. Other measured data are not affected; however, the errors significantly change the interpretation and conclusions, and thus warrant withdrawal and…
We investigate Tikhonov regularization methods for nonlinear ill-posed problems in Banach spaces, where the penalty term is described by Bregman distances. We prove convergence and stability results. Moreover, using appropriate source…
The paper has been withdrawn by the author.
Functional autoregressive models of order one (FAR(1)) are predominantly estimated by projecting curves onto leading functional principal components and fitting a vector autoregression in score space, requiring a discrete truncation level…