1.8k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Chinese University of Hong KongHK197 papers
- Shenzhen Research Institute of Big DataCN158 papers
- Chinese Academy of SciencesCN61 papers
- The University of TokyoJP53 papers
- Tsinghua UniversityCN51 papers
- Shinshu UniversityJP42 papers
- University of Hong KongHK41 papers
- University of Science and Technology of ChinaCN39 papers
- University of MünsterDE33 papers
- National University of SingaporeSG28 papers
- Nagoya UniversityJP27 papers
- Peking UniversityCN26 papers
Showing 2022 · cs.LGShow all
2 papers · 2 filters
cs.LG2022★ 3 cited
Gradient descent provably escapes saddle points in the training of shallow ReLU networks
Patrick Cheridito, Arnulf Jentzen, Florian Rossmannek
Dynamical systems theory has recently been applied in optimization to prove that gradient descent algorithms bypass so-called strict saddle points of the loss function. However, in…
cs.LG2022★ 3 cited
Efficient-Adam: Communication-Efficient Distributed Adam
Congliang Chen, Li Shen, Wei Liu +1
Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex optimization, such as training deep learning models. However, their communication c…