Xueqiong Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xueqiong Yuan has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Ercan Engin Kuruoglu
Tsinghua University
2 shared publications Jipeng Li
2 shared publicationsErcan Engin Kuruoglu
1 shared publication- Jipeng Li
Tsinghua Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Shenzhen, Guangdong, China
1 shared publication
Latest Publications
- 7 October 2025
- Published by Elsevier in Signal Processing
- Vol. 239
Improved post training quantization for heavy tailed model parameters in neural network
- 7 October 2025
- Published by Elsevier in Signal Processing
- Vol. 239
Improved post training quantization for heavy tailed model parameters in neural network
- 20 September 2024
- Published by Elsevier in Digital Signal Processing
- Vol. 156
Robustness enhancement in neural networks with alpha-stable training noise
- 20 September 2024
- Published by Elsevier in Digital Signal Processing
- Vol. 156
Robustness enhancement in neural networks with alpha-stable training noise
- 5 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (11) , 5519-5529
Exploring Weight Distributions and Dependence in Neural Networks With $\alpha$-Stable Distributions
The fundamental use of neural networks is in providing a nonlinear mapping between input and output data with possibly a high number of parameters that can be learned from data directly. Consequently, studying the model’s parameters, particularly the weights, is of paramount importance. The distribution and interdependencies of these weights have a direct impact on the model’s generalizability, compressibility, initialization, and convergence speed. By fitting the weights of pretrained neural networks using the α-stable distributions and conducting statistical tests, we discover widespread heavy-tailed phenomena in neural network weights, with a few layers exhibiting asymmetry. Additionally, we employ a multivariate α-stable distribution to model the weights and explore the relationship between weights within and across layers by calculating the signed symmetric covariation coefficient. The results reveal a strong dependence among certain weights. Our findings indicate that the Gaussian assumption, symmetry assumption, and independence assumption commonly used in neural network research might be inconsistent with reality. In conclusion, our research shows three properties observed in neural network weights: heavy-tailed phenomena, asymmetry and dependence on certain weights.
- 5 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (11) , 5519-5529
Exploring Weight Distributions and Dependence in Neural Networks With $\alpha$-Stable Distributions
The fundamental use of neural networks is in providing a nonlinear mapping between input and output data with possibly a high number of parameters that can be learned from data directly. Consequently, studying the model’s parameters, particularly the weights, is of paramount importance. The distribution and interdependencies of these weights have a direct impact on the model’s generalizability, compressibility, initialization, and convergence speed. By fitting the weights of pretrained neural networks using the α-stable distributions and conducting statistical tests, we discover widespread heavy-tailed phenomena in neural network weights, with a few layers exhibiting asymmetry. Additionally, we employ a multivariate α-stable distribution to model the weights and explore the relationship between weights within and across layers by calculating the signed symmetric covariation coefficient. The results reveal a strong dependence among certain weights. Our findings indicate that the Gaussian assumption, symmetry assumption, and independence assumption commonly used in neural network research might be inconsistent with reality. In conclusion, our research shows three properties observed in neural network weights: heavy-tailed phenomena, asymmetry and dependence on certain weights.