2.3k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Shuguang Cui5 profiles29 · h 63
- Arnulf Jentzen22 · h 49
- Z. Luo18 · h 89
- Guangxu Zhu5 profiles17 · h 33
- Xiaoguang Han2 profiles15 · h 42
- Hang Li2 profiles13 · h 18
- Tsung-Hui Chang11 · h 45
- Qingjiang Shi3 profiles9 · h 36
- H. Poor2 profiles7 · h 141
- Rui Zhang3 profiles7 · h 137
- Shiyin Li7 · h 21
- Xiaoyang Li2 profiles7 · h 9
- Chinese University of Hong Kong, ShenzhenCN158 papers
- University of MünsterDE21 papers
- Chinese University of Hong KongHK16 papers
- University of Hong KongHK15 papers
- ETH ZurichCH14 papers
- Sun Yat-sen UniversityCN13 papers
- National University of SingaporeSG12 papers
- Peng Cheng LaboratoryCN10 papers
- Princeton UniversityUS10 papers
- Tongji UniversityCN10 papers
- Beijing University of Posts and TelecommunicationsCN9 papers
- Chinese Academy of SciencesCN9 papers
4 papers · 2 filters
Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation
Simon Eberle, Arnulf Jentzen, Adrian Riekert +1
The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially…
Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation
Arnulf Jentzen, Adrian Riekert
Gradient descent (GD) type optimization schemes are the standard methods to train artificial neural networks (ANNs) with rectified linear unit (ReLU) activation. Such schemes can b…
An Efficient Learning Framework For Federated XGBoost Using Secret Sharing And Distributed Optimization
Lunchen Xie, Jiaqi Liu, Songtao Lu +2
XGBoost is one of the most widely used machine learning models in the industry due to its superior learning accuracy and efficiency. Targeting at data isolation issues in the big d…
Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions
Patrick Cheridito, Arnulf Jentzen, Florian Rossmannek
In this paper, we analyze the landscape of the true loss of neural networks with one hidden layer and ReLU, leaky ReLU, or quadratic activation. In all three cases, we provide a co…