Adaptive Structural Hyper-Parameter Configuration by Q-Learning

被引：0
|
作者：
Zhang, Haotian [1 ]
Sun, Jianyong [1 ]
Xu, Zongben [1 ]
机构：
[1] Xi An Jiao Tong Univ, Sch Math & Stat, Natl Engn Lab Big Data Analyt, Xian, Peoples R China
来源：
2020 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) | 2020年
基金：
中国国家自然科学基金; 美国国家科学基金会;
关键词：
Reinforcement learning; evolutionary algorithm; hyper-parameter tuning; Q-learning; EVOLUTION STRATEGY; ADAPTATION;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Tuning hyper-parameters for evolutionary algorithms is an important issue in computational intelligence. Performance of an evolutionary algorithm depends not only on its operation strategy design, but also on its hyper-parameters. Hyper-parameters can be categorized in two dimensions as structural/numerical and time-invariant/time-variant. Particularly, structural hyper-parameters in existing studies are usually tuned in advance for time-invariant parameters, or with hand-crafted scheduling for time-invariant parameters. In this paper, we make the first attempt to model the tuning of structural hyper-parameters as a reinforcement learning problem, and present to tune the structural hyper-parameter which controls computational resource allocation in the CEC 2018 winner algorithm by Q-learning. Experimental results show favorably against the winner algorithm on the CEC 2018 test functions.
引用
收藏
页数：8
相关论文
共 50 条
  • [31] MOEA/D with adaptive weight vector adjustment and parameter selection based on Q-learning
    Xue, Fei
    Chen, Yuezheng
    Dong, Tingting
    Wang, Peiwen
    Fan, Wenyu
    APPLIED INTELLIGENCE, 2025, 55 (06)
  • [32] Hyper-Parameter Optimization Using MARS Surrogate for Machine-Learning Algorithms
    Li, Yangyang
    Liu, Guangyuan
    Lu, Gao
    Jiao, Licheng
    Marturi, Naresh
    Shang, Ronghua
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2020, 4 (03): : 287 - 297
  • [33] Hyper-parameter optimization of deep learning model for prediction of Parkinson's disease
    Kaur, Sukhpal
    Aggarwal, Himanshu
    Rani, Rinkle
    MACHINE VISION AND APPLICATIONS, 2020, 31 (05)
  • [34] A review of automatic selection methods for machine learning algorithms and hyper-parameter values
    Luo, Gang
    NETWORK MODELING AND ANALYSIS IN HEALTH INFORMATICS AND BIOINFORMATICS, 2016, 5 (01):
  • [35] Gradient Hyper-parameter Optimization for Manifold Regularization
    Becker, Cassiano O.
    Ferreira, Paulo A. V.
    2013 12TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2013), VOL 2, 2013, : 339 - 344
  • [36] Cultural Events Classification using Hyper-parameter Optimization of Deep Learning Technique
    Feng Zhipeng
    Gani, Hamdan
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2021, 12 (05) : 603 - 609
  • [37] A GPU Scheduling Framework to Accelerate Hyper-Parameter Optimization in Deep Learning Clusters
    Son, Jaewon
    Yoo, Yonghyuk
    Kim, Khu-rai
    Kim, Youngjae
    Lee, Kwonyong
    Park, Sungyong
    ELECTRONICS, 2021, 10 (03) : 1 - 15
  • [38] Hyper-parameter Tuning for Progressive Learning and its Application to Network Cyber Security
    Karn, Rupesh Raj
    Ziegler, Matthew
    Jung, Jinwook
    Elfadel, Ibrahim M.
    2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 1220 - 1224
  • [39] Total Variation with Automatic Hyper-Parameter Estimation
    Nascimento, Jacinto
    Sanches, Joao
    2008 30TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-8, 2008, : 443 - +
  • [40] A study on depth classification of defects by machine learning based on hyper-parameter search
    Chen, Haoze
    Zhang, Zhijie
    Yin, Wuliang
    Zhao, Chenyang
    Wang, Fengxiang
    Li, Yanfeng
    MEASUREMENT, 2022, 189
12345