Active multiple matrix completion with ...
Type de document :
Communication dans un congrès avec actes
Titre :
Active multiple matrix completion with adaptive confidence sets
Auteur(s) :
Locatelli, Andrea [Auteur]
Otto-von-Guericke-Universität Magdeburg = Otto-von-Guericke University [Magdeburg] [OVGU]
Carpentier, Alexandra [Auteur]
Otto-von-Guericke-Universität Magdeburg = Otto-von-Guericke University [Magdeburg] [OVGU]
Valko, Michal [Auteur]
Sequential Learning [SEQUEL]
DeepMind [Paris]
Otto-von-Guericke-Universität Magdeburg = Otto-von-Guericke University [Magdeburg] [OVGU]
Carpentier, Alexandra [Auteur]
Otto-von-Guericke-Universität Magdeburg = Otto-von-Guericke University [Magdeburg] [OVGU]
Valko, Michal [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Sequential Learning [SEQUEL]
DeepMind [Paris]
Titre de la manifestation scientifique :
International Conference on Artificial Intelligence and Statistics
Ville :
Okinawa
Pays :
Japon
Date de début de la manifestation scientifique :
2019
Discipline(s) HAL :
Statistiques [stat]/Machine Learning [stat.ML]
Résumé en anglais : [en]
In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simultaneously. At each round, the learner can choose from which matrix it ...
Lire la suite >In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simultaneously. At each round, the learner can choose from which matrix it receives a sample from an entry drawn uniformly at random. Our main practical motivation is market segmentation, where the matrices represent different regions with different preferences of the customers. The challenge in this setting is that each of the matrices can be of a different size and also of a different rank which is unknown. We provide and analyze a new algorithm, MALocate that is able to adapt to the unknown ranks of the different matrices. We then give a lower-bound showing that our strategy is minimax-optimal and demonstrate its performance with synthetic experiments.Lire moins >
Lire la suite >In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simultaneously. At each round, the learner can choose from which matrix it receives a sample from an entry drawn uniformly at random. Our main practical motivation is market segmentation, where the matrices represent different regions with different preferences of the customers. The challenge in this setting is that each of the matrices can be of a different size and also of a different rank which is unknown. We provide and analyze a new algorithm, MALocate that is able to adapt to the unknown ranks of the different matrices. We then give a lower-bound showing that our strategy is minimax-optimal and demonstrate its performance with synthetic experiments.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.inria.fr/hal-02387468/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-02387468/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-02387468/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- Active_block_matrix_completion_with_adaptive_confidence_sets.pdf
- Accès libre
- Accéder au document