Regularized Loss
Regularized Loss is a loss function that incorporates an additional penalty term derived from a regularization method to control model complexity and prevent overfitting by balancing empirical risk minimization with structural risk minimization.
375
Publications
29.2K
Citations
1K
Authors
405
Institutions
Publications per year
2017–2026
197
Variants
Regularized Loss Function
Parents
375
EnlightenGAN: Deep Light Enhancement Without Paired Supervision
Yifan Jiang, Xinyu Gong, Ding Liu et al. · IEEE Transactions on Image Processing · 2021 · 2.4K citations
Stochastic dual coordinate ascent methods for regularized loss
Shai Shalev‐Shwartz, Tong Zhang · 2013 · 700 citations
A Comprehensive Survey of Loss Functions in Machine Learning
Qi Wang, Yue Ma, Kun Zhao et al. · Annals of Data Science · 2020 · 693 citations
1–5 of 375
1K
10
h-index
6
h-index
6
h-index
6
h-index
5
h-index
1–5 of 1K
405

Chinese Academy of Sciences
Beijing, China
15 h-index
28 publications
5.5K citations
University of California, Berkeley
Berkeley, United States
10 h-index
20 publications
1.9K citations
Massachusetts Institute of Technology
Cambridge, United States
9 h-index
21 publications
2.6K citations

Centre National de la Recherche Scientifique
Paris, France
8 h-index
13 publications
390 citations

City University of Hong Kong
Hong Kong, Hong Kong
8 h-index
16 publications
977 citations
Hebrew University of Jerusalem
Jerusalem, Israel
7 h-index
8 publications
1.3K citations
Microsoft (United States)
Redmond, United States
7 h-index
12 publications
4.1K citations

Peking University
Beijing, China
7 h-index
11 publications
2.8K citations
1–8 of 405
Repository · 65 publications · 4.1K citations
31
h-index
12 publications · 511 citations
11
h-index
Conference · 9 publications · 935 citations
9
h-index
8 publications · 364 citations
8
h-index
7 publications · 198 citations
6
h-index
1–5