Mini-Batch Learning is a machine learning optimization technique that iteratively updates model parameters using small, randomly sampled subsets of the training data, thereby balancing the computational efficiency of stochastic gradient descent with the stability and convergence properties of batch gradient descent.
463
Publications
92.7K
Citations
1.4K
Authors
426
Institutions
Publications per year
2017–2026
328
Parents
Publications
463
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Priya Goyal, Piotr Dollár, Ross Girshick et al. · arXiv (Cornell University) · 2017 · 2.6K citations · Full text
Deep Interest Network for Click-Through Rate Prediction
Guorui Zhou, Xiaoqiang Zhu, Chenru Song et al. · 2018 · 2K citations
1–5 of 463
Authors
1.4K
- PR
10
h-index
- NS
8
h-index
- MT
7
h-index
- YS
5
h-index
- OD
5
h-index
1–5 of 1.4K
Institutions
426
Google (United States)
Mountain View, United States
17 h-index
33 publications
68.3K citations
Carnegie Mellon University
Pittsburgh, United States
11 h-index
23 publications
3.9K citations
University of California, Berkeley
Berkeley, United States
11 h-index
20 publications
2.1K citations
University of Edinburgh
Edinburgh, United Kingdom
8 h-index
13 publications
1.2K citations
Microsoft (United States)
Redmond, United States
8 h-index
14 publications
750 citations
Toyota Technological Institute at Chicago
Chicago, United States
8 h-index
15 publications
1K citations
Princeton University
Princeton, United States
7 h-index
10 publications
993 citations
Tsinghua University
Beijing, China
7 h-index
14 publications
697 citations
1–8 of 426
Venues
- arXiv (Cornell University)
Repository · 145 publications · 64.2K citations
47
h-index
- Neural Information Processing Systems
Conference · 12 publications · 1.6K citations
11
h-index
- Neurocomputing
10 publications · 305 citations
10
h-index
- International Conference on Machine Learning
Conference · 9 publications · 795 citations
9
h-index
- IEEE Access
6 publications · 220 citations
6
h-index
1–5