A simple dynamic bandit algorithm for ...
Document type :
Communication dans un congrès avec actes
Title :
A simple dynamic bandit algorithm for hyper-parameter tuning
Author(s) :
Shang, Xuedong [Auteur]
Sequential Learning [SEQUEL]
Kaufmann, Emilie [Auteur]
Sequential Learning [SEQUEL]
Valko, Michal [Auteur]
DeepMind [Paris]
Sequential Learning [SEQUEL]
Sequential Learning [SEQUEL]
Kaufmann, Emilie [Auteur]
Sequential Learning [SEQUEL]
Valko, Michal [Auteur]
DeepMind [Paris]
Sequential Learning [SEQUEL]
Conference title :
Workshop on Automated Machine Learning at International Conference on Machine Learning
Conference organizers(s) :
AutoML@ICML 2019 - 6th ICML Workshop on Automated Machine Learning
City :
Long Beach
Country :
Etats-Unis d'Amérique
Start date of the conference :
2019-06-14
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [en]
Hyper-parameter tuning is a major part of modern machine learning systems. The tuning itself can be seen as a sequential resource allocation problem. As such, methods for multi-armed bandits have been already applied. In ...
Show more >Hyper-parameter tuning is a major part of modern machine learning systems. The tuning itself can be seen as a sequential resource allocation problem. As such, methods for multi-armed bandits have been already applied. In this paper, we view hyper-parameter optimization as an instance of best-arm identification in infinitely many-armed bandits. We propose D-TTTS, a new adaptive algorithm inspired by Thompson sampling, which dynamically balances between refining the estimate of the quality of hyper-parameter configurations previously explored and adding new hyper-parameter configurations to the pool of candidates. The algorithm is easy to implement and shows competitive performance compared to state-of-the-art algorithms for hyper-parameter tuning.Show less >
Show more >Hyper-parameter tuning is a major part of modern machine learning systems. The tuning itself can be seen as a sequential resource allocation problem. As such, methods for multi-armed bandits have been already applied. In this paper, we view hyper-parameter optimization as an instance of best-arm identification in infinitely many-armed bandits. We propose D-TTTS, a new adaptive algorithm inspired by Thompson sampling, which dynamically balances between refining the estimate of the quality of hyper-parameter configurations previously explored and adding new hyper-parameter configurations to the pool of candidates. The algorithm is easy to implement and shows competitive performance compared to state-of-the-art algorithms for hyper-parameter tuning.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-02145200/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02145200/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02145200/document
- Open access
- Access the document
- document
- Open access
- Access the document
- shang2019simple.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- shang2019simple.pdf
- Open access
- Access the document