Zhenyu LiaoAssociate researcher Doctoral Degree in Engineering
廖振宇，于法国巴黎萨克雷大学获数学与计算机博士学位，后在美国加州大学伯克利分校统计系和ICSI从事博士后研究工作，2021年起至今在华中科技大学电信学院工作，任副研究员。 主要研究方向是机器学习理论与应用、高维统计和随机矩阵理论，成果发表在ICML、NeurIPS、ICLR、COLT、IEEE汇刊和AAP等机器学习和数据处理的会议与期刊，合著专著Random Matrix Methods for Machine Learning。任ICML、NeurIPS、ICLR、AISTATS和IJCNN等...details>
Associate researcher
Supervisor of Doctorate Candidates
Supervisor of Master's Candidates
Department:School of Electronic Information and Communications
ZipCode:
Email:
-
Research Focus
No content -
Social Affiliations
IEEE高级会员，任中国现场统计研究会随机矩阵理论与应用分会副秘书长、大数据统计分会理事，中国商业统计学会人工智能分会理事。
任ICML、NeurIPS、ICLR、AISTATS和IJCNN等会议的领域主席和Statistics and Computing期刊编委。
-
Education Experience
2010/9-2014/6华中科技大学 Bachelor's Degree in Engineering | Undergraduate (Bachelor’s degree)
2014/9-2019/12法国中央高等电力学校 Doctoral Degree in Engineering | Postgraduate (Doctoral)
-
Work Experience
2020/1-2020/12统计系 | 加州大学伯克利分校 | 博士后研究员
- 1.Cosme Louart, Zhenyu Liao, and Romain Couillet. A Random Matrix Approach to Neural Networks. The Annals of Applied Probability 28(2) (Apr. 2018), 1190–1248.
- 2.Zhenyu Liao and Romain Couillet. A Large Dimensional Analysis of Least Squares Support Vector Machines. IEEE Transactions on Signal Processing 67(4) (Feb. 2019), 1065–1074.
- 3.Zhenyu Liao, Romain Couillet, and Michael W Mahoney. A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent. Journal of Statistical Mechanics: Theory and Experiment 2021(12) (Dec. 2021),...
- 4.Zhenyu Liao and Romain Couillet. On the Spectrum of Random Features Maps of High Dimensional Data. International Conference on Machine Learning (ICML). Vol. 80. PMLR, July, 2018, pp.3063–3071.
- 5.Zhenyu Liao and Romain Couillet. The Dynamics of Learning: A Random Matrix Approach. International Conference on Machine Learning (ICML). Vol. 80. PMLR, July 2018, pp.3072–3081.
- 6.Michal Derezinski, Feynman T Liang, Zhenyu Liao, and Michael W. Mahoney. Precise expressions for random projections: Low-rank approximation and randomized Newton. Advances in Neural Information Processing Systems (NeurIPS). Vol. 33. Curran Associates, Inc., 2020, pp.18272–182...
Research Group
No content