Colin Wei
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Statistical and Nonlinear Physics
- Computational Mechanics
- Signal Processing
- Co-authors
- Tengyu MaYining ChenJason D. LeeQiang LiuYuanzhi LiStefano Ermon
- Topics
- Neural Networks and Applications (3 papers)Advanced Neural Network Applications (3 papers)Machine Learning and ELM (3 papers)
- Cited by
- Artificial IntelligenceComputer Vision and Pattern RecognitionStatistical and Nonlinear Physics
- Journals
- arXiv (Cornell University)neural information processing systemsNeural Information Processing Systems
- Partner nations
- United States
In The Last Decade
Colin Wei
7 papers receiving 71 citations
Peers
Comparison fields: 5 of 27
- Artificial Intelligence 63
- Computer Vision and Pattern Recognition 28
- Statistical and Nonlinear Physics 8
- Computational Mechanics 8
- Signal Processing 4
Countries citing papers authored by Colin Wei
This map shows the geographic impact of Colin Wei'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 Colin Wei with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Colin Wei more than expected).
Fields of papers citing papers by Colin Wei
This network shows the impact of papers produced by Colin Wei. 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 Colin Wei. The network helps show where Colin Wei may publish in the future.
Co-authorship network of co-authors of Colin Wei
This figure shows the co-authorship network connecting the top 25 collaborators of Colin Wei. A scholar is included among the top collaborators of Colin Wei based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Colin Wei. Colin Wei is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 0 | |
| 2 | Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin | 2 |
| 3 | Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data | 32 |
| 4 | Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation | 3 |
| 5 | Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks | 6 |
| 6 | Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel | 16 |
| 7 | On the Margin Theory of Feedforward Neural Networks | 12 |
| 8 | 1 |
About Colin Wei
Colin Wei is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Signal Processing, having authored 8 papers that have together received 72 indexed citations. Recurring topics across this work include Neural Networks and Applications (3 papers), Advanced Neural Network Applications (3 papers) and Machine Learning and ELM (3 papers). The work is most often cited by research in Artificial Intelligence (63 citations), Computer Vision and Pattern Recognition (28 citations) and Statistical and Nonlinear Physics (8 citations). Colin Wei has collaborated with scholars based in United States. Frequent co-authors include Tengyu Ma, Yining Chen, Jason D. Lee, Tengyu Ma, Qiang Liu, Qiang Liu, Yuanzhi Li and Stefano Ermon. Their work appears in journals such as arXiv (Cornell University), neural information processing systems and Neural Information Processing Systems.
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.