Stochastic Online Linear Regression: the ...
Type de document :
Communication dans un congrès avec actes
Titre :
Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge
Auteur(s) :
Ouhamma, Reda [Auteur]
Scool [Scool]
Université de Lille
Inria Lille - Nord Europe
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Maillard, Odalric [Auteur]
Inria Lille - Nord Europe
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Perchet, Vianney [Auteur]
Centre de Recherche en Economie et Statistique [Bruz] [CREST]
Scool [Scool]
Université de Lille
Inria Lille - Nord Europe
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Maillard, Odalric [Auteur]
Inria Lille - Nord Europe
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Perchet, Vianney [Auteur]
Centre de Recherche en Economie et Statistique [Bruz] [CREST]
Titre de la manifestation scientifique :
NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems
Ville :
Virtual
Pays :
Canada
Date de début de la manifestation scientifique :
2021-12-06
Titre de la revue :
NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems
Discipline(s) HAL :
Informatique [cs]
Mathématiques [math]
Mathématiques [math]
Résumé en anglais : [en]
We consider the problem of online linear regression in the stochastic setting. We derive high probability regret bounds for online ridge regression and the forward algorithm. This enables us to compare online regression ...
Lire la suite >We consider the problem of online linear regression in the stochastic setting. We derive high probability regret bounds for online ridge regression and the forward algorithm. This enables us to compare online regression algorithms more accurately and eliminate assumptions of bounded observations and predictions. Our study advocates for the use of the forward algorithm in lieu of ridge due to its enhanced bounds and robustness to the regularization parameter. Moreover, we explain how to integrate it in algorithms involving linear function approximation to remove a boundedness assumption without deteriorating theoretical bounds. We showcase this modification in linear bandit settings where it yields improved regret bounds. Last, we provide numerical experiments to illustrate our results and endorse our intuitions.Lire moins >
Lire la suite >We consider the problem of online linear regression in the stochastic setting. We derive high probability regret bounds for online ridge regression and the forward algorithm. This enables us to compare online regression algorithms more accurately and eliminate assumptions of bounded observations and predictions. Our study advocates for the use of the forward algorithm in lieu of ridge due to its enhanced bounds and robustness to the regularization parameter. Moreover, we explain how to integrate it in algorithms involving linear function approximation to remove a boundedness assumption without deteriorating theoretical bounds. We showcase this modification in linear bandit settings where it yields improved regret bounds. Last, we provide numerical experiments to illustrate our results and endorse our intuitions.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.inria.fr/hal-03410901/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-03410901/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-03410901/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- Neurips_Forward_Algo.pdf
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- Neurips_Forward_Algo.pdf
- Accès libre
- Accéder au document