Skip to Main content Skip to Navigation
Conference papers

QIM: Quantifying Hyperparameter Importance for Deep Learning

Abstract : Recently, Deep Learning (DL) has become super hot because it achieves breakthroughs in many areas such as image processing and face identification. The performance of DL models critically depend on hyperparameter settings. However, existing approaches that quantify the importance of these hyperparameters are time-consuming.In this paper, we propose a fast approach to quantify the importance of the DL hyperparameters, called QIM. It leverages Plackett-Burman design to collect as few as possible data but can still correctly quantify the hyperparameter importance. We conducted experiments on the popular deep learning framework – Caffe – with different datasets to evaluate QIM. The results show that QIM can rank the importance of the DL hyperparameters correctly with very low cost.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/hal-01648007
Contributor : Hal Ifip <>
Submitted on : Friday, November 24, 2017 - 4:49:19 PM
Last modification on : Friday, November 24, 2017 - 4:50:58 PM

File

432484_1_En_15_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Dan Jia, Rui Wang, Chengzhong Xu, Zhibin Yu. QIM: Quantifying Hyperparameter Importance for Deep Learning. 13th IFIP International Conference on Network and Parallel Computing (NPC), Oct 2016, Xi'an, China. pp.180-188, ⟨10.1007/978-3-319-47099-3_15⟩. ⟨hal-01648007⟩

Share

Metrics

Record views

272

Files downloads

283