Mixability made efficient: Fast online multiclass logistic regression - Apprentissage de modèles visuels à partir de données massives Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Mixability made efficient: Fast online multiclass logistic regression

Résumé

Mixability has been shown to be a powerful tool to obtain algorithms with optimal regret. However, the resulting methods often suffer from high computational complexity which has reduced their practical applicability. For example, in the case of multiclass logistic regression, the aggregating forecaster (Foster et al. (2018)) achieves a regret of $O(\log(Bn))$ whereas Online Newton Step achieves $O(e^B\log(n))$ obtaining a double exponential gain in $B$ (a bound on the norm of comparative functions). However, this high statistical performance is at the price of a prohibitive computational complexity $O(n^{37})$.
Fichier principal
Vignette du fichier
MulticlassLogistic.pdf (2.45 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03370530 , version 1 (08-10-2021)

Identifiants

Citer

Rémi Jézéquel, Pierre Gaillard, Alessandro Rudi. Mixability made efficient: Fast online multiclass logistic regression. NeurIPS 2021. Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Online, France. ⟨hal-03370530⟩
149 Consultations
101 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More