E
Ernesto De Vito
Researcher at University of Genoa
Publications - 91
Citations - 2501
Ernesto De Vito is an academic researcher from University of Genoa. The author has contributed to research in topics: Shearlet & Kernel (statistics). The author has an hindex of 19, co-authored 89 publications receiving 2161 citations. Previous affiliations of Ernesto De Vito include University of Modena and Reggio Emilia.
Papers
More filters
Journal ArticleDOI
Are loss functions all the same
TL;DR: A convexity assumption is introduced, which is met by all loss functions commonly used in the literature, and how the bound on the estimation error changes with the loss is studied.
Journal ArticleDOI
On Learning with Integral Operators
TL;DR: A technique based on a concentration inequality for Hilbert spaces is used to provide new much simplified proofs for a number of results in spectral approximation of graph Laplacian operator extending and strengthening results from von Luxburg et al. (2008).
Journal ArticleDOI
Vector valued reproducing kernel hilbert spaces of integrable functions and mercer theorem
TL;DR: In this paper, the authors characterize the reproducing kernel Hilbert spaces whose elements are p-integrable functions in terms of the boundedness of the integral operator whose kernel is the Reproducing Kernel.
Journal ArticleDOI
Elastic-net regularization in learning theory
TL;DR: It is proved that there exists a particular ''elastic-net representation'' of the regression function such that, if the number of data increases, the elastic-net estimator is consistent not only for prediction but also for variable/feature selection.
Journal ArticleDOI
Learning from Examples as an Inverse Problem
TL;DR: A natural extension of analysis of Tikhonov regularization to the continuous (population) case and study the interplay between the discrete and continuous problems allows to draw a clear connection between the consistency approach in learning theory and the stability convergence property in ill-posed inverse problems.