Hyperparameter Optimization
Hyperparameter Optimization is the systematic process of selecting optimal hyperparameter values for a machine learning model by exploring the hyperparameter space to maximize model performance on a given task, distinguished from general model training by its focus on tuning fixed structural parameters prior to learning.
2K
Publications
190.5K
Citations
7.3K
Authors
2.2K
Institutions
Publications per year
2017–2026
1.8K
2K
Convolutional Neural Networks for Sentence Classification
Random search for hyper-parameter optimization
James Bergstra, Yoshua Bengio · 2012 · 7.9K citations
Takuya Akiba, Shotaro Sano, Toshihiko Yanase et al. · 2019 · 7.4K citations
1–5 of 2K
7.3K
21
h-index
13
h-index
11
h-index
11
h-index
10
h-index
1–5 of 7.3K
2.2K
Google (United States)
Mountain View, United States
25 h-index
102 publications
38.2K citations
Princess Nourah bint Abdulrahman University
Riyadh, Saudi Arabia
23 h-index
44 publications
1.5K citations
Prince Sattam Bin Abdulaziz University
Al Kharj, Saudi Arabia
19 h-index
45 publications
1.5K citations
Massachusetts Institute of Technology
Cambridge, United States
19 h-index
89 publications
13.2K citations
King Khalid University
Abhā, Saudi Arabia
18 h-index
24 publications
843 citations
Harvard University
Cambridge, United States
18 h-index
52 publications
15K citations

Centre National de la Recherche Scientifique
Paris, France
18 h-index
56 publications
5K citations

King Saud University
Riyadh, Saudi Arabia
16 h-index
21 publications
1.8K citations
1–8 of 2.2K
Repository · 257 publications · 27.1K citations
62
h-index
65 publications · 3.6K citations
33
h-index
33 publications · 2K citations
25
h-index
36 publications · 1.4K citations
24
h-index
28 publications · 1.7K citations
23
h-index
1–5