Simon S. Du
Impact in
- Computational Mathematics top 10%
- Artificial Intelligence top 5%
- Stochastic Gradient Optimization Techniques
- Neural Networks and Applications
- Machine Learning and ELM
- Reinforcement Learning in Robotics
- Domain Adaptation and Few-Shot Learning
Papers in
-
- Stochastic Gradient Optimization Techniques 10
- Reinforcement Learning in Robotics 8
- Machine Learning and Algorithms 7
- Domain Adaptation and Few-Shot Learning 7
- Machine Learning and ELM 6
-
- Advanced Neural Network Applications 5
- Co-authors
- Jason D. Lee (5 shared papers)Ruosong Wang (7 shared papers)Ruslan Salakhutdinov (2 shared papers)Michael I. Jordan (2 shared papers)Weijie Su (2 shared papers)Sanjeev Arora (3 shared papers)Zhiyuan Li (1 shared paper)Wei Hu (1 shared paper)
- Journals
- Information Fusion (1 paper)Journal of the ACM (1 paper)Mathematical Programming (1 paper)INFORMS journal on computing (1 paper)International Conference on Learning Representations (2 papers)
- Partner nations
- United StatesChinaJapan
In The Last Decade
Simon S. Du
34 papers receiving 473 citations
Peers
Comparison fields: 5 of 76
- Computational Mathematics 11
- Artificial Intelligence 340
- Statistical and Nonlinear Physics 67
- Numerical Analysis 29
- Computer Vision and Pattern Recognition 109
Countries citing papers authored by Simon S. Du
This map shows the geographic impact of Simon S. Du's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Simon S. Du with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Simon S. Du more than expected).
Fields of papers citing papers by Simon S. Du
This network shows the impact of papers produced by Simon S. Du. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Simon S. Du. The network helps show where Simon S. Du may publish in the future.
Co-authors
The 25 scholars most cited alongside Simon S. Du, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 40 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | On Exact Computation with an Infinitely Wide Neural Net | 2019 | 107 |
| 2 | Gradient descent finds global minima of deep neural networks | 2019 | 75 |
| 3 | 2021 | 75 | |
| 4 | On the Power of Over-parametrization in Neural Networks with Quadratic Activation | 2018 | 42 |
| 5 | 2017 | 21 | |
| 6 | 2022 | 19 | |
| 7 | 2019 | 17 | |
| 8 | Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels | 2019 | 16 |
| 9 | 2023 | 14 | |
| 10 | When is a convolutional filter easy to learn | 2018 | 14 |
| 11 | Stochastic Zeroth-order Optimization in High Dimensions. | 2017 | 11 |
| 12 | What Can Neural Networks Reason About | 2020 | 11 |
| 13 | Computationally Efficient Robust Sparse Estimation in High Dimensions | 2017 | 10 |
| 14 | 2019 | 10 | |
| 15 | 2021 | 10 | |
| 16 | Hypothesis Transfer Learning via Transformation Functions | 2017 | 9 |
| 17 | How Many Samples are Needed to Learn a Convolutional Neural Network | 2018 | 7 |
| 18 | How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks | 2021 | 6 |
| 19 | Spectral Gap Error Bounds for Improving CUR Matrix Decomposition and the Nystrom Method | 2015 | 4 |
| 20 | Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle | 2019 | 4 |
About Simon S. Du
Simon S. Du is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Computational Mechanics, Management Science and Operations Research and Computational Theory and Mathematics, having authored 40 papers that have together received 507 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (10 papers), Reinforcement Learning in Robotics (8 papers), Machine Learning and Algorithms (7 papers), Domain Adaptation and Few-Shot Learning (7 papers), Sparse and Compressive Sensing Techniques (7 papers), Advanced Bandit Algorithms Research (6 papers), Machine Learning and ELM (6 papers) and Advanced Neural Network Applications (5 papers). The work is most often cited by research in Computational Mathematics (11 citations), Artificial Intelligence (340 citations), Statistical and Nonlinear Physics (67 citations), Numerical Analysis (29 citations) and Computer Vision and Pattern Recognition (109 citations). Simon S. Du has collaborated with scholars based in United States, China and Japan. Frequent co-authors include Jason D. Lee, Ruosong Wang, Ruslan Salakhutdinov, Michael I. Jordan, Weijie Su, Sanjeev Arora, Zhiyuan Li, Wei Hu, Xiyu Zhai and Liwei Wang. Their work appears in journals such as Information Fusion, Journal of the ACM, Mathematical Programming, INFORMS journal on computing and International Conference on Learning Representations.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.