Gao Peifeng

PhD student, Department of Computer Science, University of Hong Kong

Joined

November 2022

Names

Gao Peifeng (Preferred)

Emails

****@mails.ucas.ac.cn (Confirmed)

,

****@connect.hku.hk (Confirmed)

Personal Links

Career & Education History

PhD student

Department of Computer Science, University of Hong Kong (hku.hk)

2024 – 2028

Undergrad student

Department of Computer Science, University of the Chinese Academy of Sciences (ucas.ac.cn)

2021 – 2024

MS student

Department of Computer Science, Harbin Institute of Technology at Weihai (hitwh.edu.cn)

2017 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

Machine Learning

Present

Publications

Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks
Chenyang Zhang, Gao Peifeng, Difan Zou, Yuan Cao
- HiLD at ICML 2024 Poster
- Readers: Everyone
Towards Demystifying the Generalization Behaviors When Neural Collapse Emerges
Gao Peifeng, Qianqian Xu, Yibo Yang, Peisong Wen, Huiyang Shao, Zhiyong Yang, Bernard Ghanem, Qingming Huang
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Feature Directions Matters: Long-Tailed Learning via Rotated Balanced Representation
Gao Peifeng, Qianqian Xu, Peisong Wen, Zhiyong Yang, Huiyang Shao, Qingming Huang
- 12 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Towards Decision-Friendly AUC: Learning Multi-Classifier with AUCµ
Gao Peifeng, Qianqian Xu, Peisong Wen, Huiyang Shao, Yuan He, Qingming Huang
- 12 May 2023 (modified: 12 May 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
Weighted ROC Curve in Cost Space: Extending AUC to Cost-Sensitive Learning
Huiyang Shao, Qianqian Xu, Zhiyong Yang, Peisong Wen, Gao Peifeng, Qingming Huang
- NeurIPS 2023 poster
- Readers: Everyone
Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation
Gao Peifeng, Qianqian Xu, Peisong Wen, Zhiyong Yang, Huiyang Shao, Qingming Huang
- ICML 2023 Poster
- Readers: Everyone

Co-Authors