.png){kind=icon}
Return
Efficient hyperparameter optimization through model-based reinforcement learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2020.06.064.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Hyperparameter tuning is critical for the performance of machine learning algorithms. However, a noticeable limitation is the high computational cost of algorithm evaluation for complex models or for large datasets, which makes the tuning process highly inefficient. In this paper, we propose a novel model-based method for efficient hyperparameter optimization. Firstly, we frame this optimization process as a reinforcement learning problem and then employ an agent to tune hyperparameters sequentially. In addition, a model that learns how to evaluate an algorithm is used to speed up the training. However, model inaccuracy is further exacerbated by long-term use, resulting in collapse performance. We propose a novel method for controlling the model use by measuring the impact of the model on the policy and limiting it to a proper range. Thus, the horizon of the model use can be dynamically adjusted. We apply the proposed method to tune the hyperparameters of the extreme gradient boosting and convolutional neural networks on 101 tasks. The experimental results verify that the proposed method achieves the highest accuracy on 86.1% of the tasks, compared with other state-of-the-art methods and the average ranking of runtime is significant lower than all methods by using the predictive model. (C) 2020 Elsevier B.V. All rights reserved.
Keywords:
Hyperparameter optimization
Machine learning
Reinforcement learning
Journal
IF:
6.5
Papers:
2.5W
Citations:
7.2W
Organization
No organization information available
Cited Papers
ShareSaveShareSave
Pre-training the deep generative models with adaptive hyperparameter optimization.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
ShareSave
ShareSaveShareSaveShareSaveRobot skill acquisition in assembly process using deep reinforcement learningNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
ShareSaveShareSave no more
no more