Active multiple matrix completion with ...
Document type :
Communication dans un congrès avec actes
Title :
Active multiple matrix completion with adaptive confidence sets
Author(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]
DeepMind [Paris]
Sequential Learning [SEQUEL]
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]

DeepMind [Paris]
Sequential Learning [SEQUEL]
Conference title :
International Conference on Artificial Intelligence and Statistics
City :
Okinawa
Country :
Japon
Start date of the conference :
2019
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-02387468/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02387468/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02387468/document
- Open access
- Access the document
- document
- Open access
- Access the document
- Active_block_matrix_completion_with_adaptive_confidence_sets.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- Active_block_matrix_completion_with_adaptive_confidence_sets.pdf
- Open access
- Access the document