Operator-Valued Kernels for Nonparametric Operator Estimation - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2011

Operator-Valued Kernels for Nonparametric Operator Estimation


We consider the supervised learning problem when both covariates and responses are real functions rather than scalars or finite dimensional vectors. In this setting, we aim at developing a sound and effective nonparametric operator estimation approach based on optimal approximation in reproducing kernel Hilbert spaces of function-valued functions. In a first step, we exhibit a class of operator-valued kernels that perform the mapping between two spaces of functions: this is the first contribution of this paper. Then, we show how to solve the problem of minimizing a regularized functional without discretizing covariate and target functions. Finally, we apply this framework to a standard functional regression problem.
Fichier principal
Vignette du fichier
RR-7607.pdf (534.6 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00587649 , version 1 (21-04-2011)


  • HAL Id : inria-00587649 , version 1


Hachem Kadri, Philippe Preux, Emmanuel Duflos, Stephane Canu. Operator-Valued Kernels for Nonparametric Operator Estimation. [Research Report] RR-7607, INRIA. 2011. ⟨inria-00587649⟩
250 View
419 Download


Gmail Facebook Twitter LinkedIn More