盖阔

个人简介

盖阔现任上海数学与交叉学科研究院助理教授。2022年毕业于中国科学院数学与系统科学研究院。随后在北京大学数学科学学院与武汉大学担任博士后研究员与特聘副研究员。他的主要研究方向聚焦在随机扰动下系统特征值的突变行为、神经网络中的特征学习理论、深度学习在生物信息学中应用等。

教育经历

• 2013-2017，School of Mathematical Sciences，Fudan University, Bachelor of Science
• 2017-2022，Academy of Mathematics and Systems Science of the Chinese Academy of Sciences，PhD in Applied Mathematics

工作经历

• 2022.9-2025.3, School of Mathematical Sciences, Peking University, Postdoctoral Researcher
• 2025.5-2025.9, School of Artificial Intelligence, Wuhan University, Assistant Professor

论著

1. Gai K, Zhang S. Tessellating the Latent Space for Non-Adversarial Generative Auto-Encoders, IEEE Transactions on Pattern Analysis and Machine Intelligence,2024
2. Zhang C.∗, Gai K∗, and Zhang S. Matrix Normal PCA for Interpretable Dimension Reduction and Graphical Noise Modeling. Pattern Recognition, 2024
3. Li S∗, Gai K∗, Dong K.∗, Zhang Y., and Zhang S. High-density Generation of Spatial Transcriptomics with STAGE. Nucleic Acids Research, 2024
4. Wang S∗, Gai K∗ and Zhang S. Progressive Feedforward Collapse of ResNet Training. IEEE Transactions on Neural Networks and Learning Systems, 2025