Self-normalization techniques for streaming confident regression - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Self-normalization techniques for streaming confident regression

Résumé

We consider, in a generic streaming regression setting, the problem of building a confidence interval (and distribution) on the next observation based on past observed data. The observations given to the learner are of the form (x, y) with y = f (x) + ξ, where x can have arbitrary dependency on the past observations, f is unknown and the noise ξ is sub-Gaussian conditionally on the past observations. Further, the observations are assumed to come from some external filtering process making the number of observations itself a random stopping time. In this challenging scenario that captures a large class of processes with non-anticipative dependencies, we study the ordinary, ridge, and kernel least-squares estimates and provide confidence intervals based on self-normalized vector-valued martingale techniques, applied to the estimation of the mean and of the variance. We then discuss how these adaptive confidence intervals can be used in order to detect a possible model mismatch as well as to estimate the future (self-information, quadratic, or transportation) loss of the learner at a next step.
Fichier principal
Vignette du fichier
HalSubmittedV2.pdf (897.83 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01349727 , version 1 (29-07-2016)
hal-01349727 , version 2 (07-03-2017)

Identifiants

  • HAL Id : hal-01349727 , version 2

Citer

Odalric-Ambrym Maillard. Self-normalization techniques for streaming confident regression. 2016. ⟨hal-01349727v2⟩
730 Consultations
814 Téléchargements

Partager

Gmail Facebook X LinkedIn More