A simple dynamic bandit algorithm for hyper-parameter tuning - Archive ouverte HAL Access content directly
Conference Papers Year :

A simple dynamic bandit algorithm for hyper-parameter tuning

(1) , (1) , (2, 1)
1
2
Xuedong Shang
Emilie Kaufmann
Michal Valko

Abstract

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.
Fichier principal
Vignette du fichier
shang2019simple.pdf (672.61 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02145200 , version 1 (01-06-2019)

Identifiers

  • HAL Id : hal-02145200 , version 1

Cite

Xuedong Shang, Emilie Kaufmann, Michal Valko. A simple dynamic bandit algorithm for hyper-parameter tuning. Workshop on Automated Machine Learning at International Conference on Machine Learning, AutoML@ICML 2019 - 6th ICML Workshop on Automated Machine Learning, Jun 2019, Long Beach, United States. ⟨hal-02145200⟩
268 View
947 Download

Share

Gmail Facebook Twitter LinkedIn More