9.2k citations
- National University of SingaporeSG76 papers
- Hong Kong University of Science and TechnologyHK70 papers
- Chinese University of Hong KongHK67 papers
- Harbin Institute of TechnologyCN57 papers
- Chinese Academy of SciencesCN56 papers
- City University of Hong KongHK52 papers
- Fudan UniversityCN47 papers
- Nanyang Technological UniversitySG46 papers
- University of Hong KongHK46 papers
- Sun Yat-sen UniversityCN44 papers
- Tongji UniversityCN42 papers
- Peking UniversityCN41 papers
65 papers · 1 filter
Robust Learning with Kernel Mean p-Power Error Loss
Badong Chen, Lei Xing, Xin Wang +2
Correntropy is a second order statistical measure in kernel space, which has been successfully applied in robust learning and signal processing. In this paper, we define a nonsecon…
Impurity-limited quantum transport variability in magnetic tunnel junctions
Jianing Zhuang, Yin Wang, Yan Zhou +2
We report an extensive first-principles investigation of impurity-induced device-to-device variability of spin-polarized quantum tunneling through Fe/MgO/Fe magnetic tunnel junctio…
A proximal difference-of-convex algorithm with extrapolation
Bo Wen, Xiaojun Chen, Ting Kei Pong
We consider a class of difference-of-convex (DC) optimization problems whose objective is level-bounded and is the sum of a smooth convex function with Lipschitz gradient, a proper…
Regularly Decomposable Tensors and Classical Spin States
Liqun Qi, Guofeng Zhang, Daniel Braun +2
A spin- state can be represented by a symmetric tensor of order and dimension . Here, can be a positive integer, which corresponds to a boson; can also be a po…
Mode Regularized Generative Adversarial Networks
Tong Che, Yanran Li, Athul Paul Jacob +2
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue t…
Improving Multi-Document Summarization via Text Classification
Ziqiang Cao, Wenjie Li, Sujian Li +1
Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents. Text classification just…