L2 Regularization is a regularization technique that belongs to the class of penalty methods in statistical learning, distinguished by its addition of the squared magnitude of coefficients as a penalty term to the loss function to prevent overfitting by promoting smaller parameter values.
350
Publications
36.1K
Citations
1.1K
Authors
440
Institutions
Publications per year
2017–2026
202
Parents
Publications
350
Decoupled Weight Decay Regularization
Ilya Loshchilov, Frank Hutter · arXiv (Cornell University) · 2017 · 9.1K citations · Full text
Efficient and Robust Feature Selection via Joint ℓ2,1-Norms Minimization
Feiping Nie, Heng Huang, Xiao Cai et al. · 2010 · 1.6K citations
1–5 of 350
Authors
1.1K
- FN
7
h-index
- WW
5
h-index
- YL
5
h-index
- ZX
4
h-index
- AA
4
h-index
1–5 of 1.1K
Institutions
440
Google (United States)
Mountain View, United States
9 h-index
14 publications
2K citations
Chinese Academy of Sciences
Beijing, China
9 h-index
22 publications
1.7K citations
Xi'an Jiaotong University
Xi'an, China
8 h-index
19 publications
1.3K citations
Dalian University of Technology
Dalian, China
8 h-index
23 publications
748 citations
Northwestern Polytechnical University
Xi'an, China
7 h-index
22 publications
1.3K citations
Stanford University
Stanford, United States
6 h-index
13 publications
3K citations
Macau University of Science and Technology
Macao, Macao
5 h-index
17 publications
481 citations
Microsoft (United States)
Redmond, United States
5 h-index
6 publications
1.2K citations
1–8 of 440
Venues
- arXiv (Cornell University)
Repository · 37 publications · 12.5K citations
23
h-index
- Neurocomputing
12 publications · 423 citations
11
h-index
- IEEE Access
9 publications · 365 citations
11
h-index
- IEEE Transactions on Neural Networks and Learning Systems
8 publications · 752 citations
8
h-index
- Applied Sciences
4 publications · 238 citations
5
h-index
1–5