arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.01751cs.LGstat.ML
收藏

基于数据到超参数映射发现的超参数自动优化

Automatic Hyper-Parameter Optimization Based on Mapping Discovery from Data to Hyper-Parameters

Harbin Institute of Technology(哈尔滨工业大学)

Bozhou Chen, Kaixin Zhang, Longshen Ou, Chenmin Ba, Hongzhi Wang, Chunnan Wang

摘要:

机器学习算法在人工智能领域取得了令人瞩目的成就。然而,大多数机器学习算法对超参数敏感。人工优化超参数是超参数整定的常用方法。然而,这是昂贵的和经验依赖。自动超参数优化(autoHPO)由于其有效性而受到青睐。然而,目前的autoHPO方法通常只对某一类问题有效,并且时间成本很高。在本文中,我们提出了一种有效的自动参数优化方法,这是基于从数据到相应的超参数的映射。为了描述这种映射,我们提出了一个复杂的网络结构。为了获得这样的映射,我们开发了有效的网络分割算法。在映射的应用过程中,我们还设计了进一步优化映射结果的策略。大量的实验结果表明,所提出的方法优于国家的最先进的approaches显着。

英文摘要:

Machine learning algorithms have made remarkable achievements in the field of artificial intelligence. However, most machine learning algorithms are sensitive to the hyper-parameters. Manually optimizing the hyper-parameters is a common method of hyper-parameter tuning. However, it is costly and empirically dependent. Automatic hyper-parameter optimization (autoHPO) is favored due to its effectiveness. However, current autoHPO methods are usually only effective for a certain type of problems, and the time cost is high. In this paper, we propose an efficient automatic parameter optimization approach, which is based on the mapping from data to the corresponding hyper-parameters. To describe such mapping, we propose a sophisticated network structure. To obtain such mapping, we develop effective network constrution algorithms. We also design strategy to optimize the result futher during the application of the mapping. Extensive experimental results demonstrate that the proposed approaches outperform the state-of-the-art apporaches significantly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑