Jiaye Teng 滕佳烨
 |
滕佳烨 |
关于我
我叫滕佳烨，现在是上海财经大学统计与管理学院的一名助理教授(2024-)。我的博士就读于清华大学交叉信息研究院 (2020-2024)，师从袁洋教授。我曾在普林斯顿大学访问 (2023)，师从Sanjeev Arora。我的本科就读于上海财经大学统计与管理学院统计学实验班 (2016-2020)，导师是柏杨教授。我当前正在我的主要研究方向是神经网络泛化理论。此外，我还关注统计理论与机器学习的结合，包括因果推断、共形预测等。 如果您对这方面感兴趣，欢迎随时联系！
实验室长期招募合作学生，并有一个博士生招生名额。如果您有兴趣，请先阅读实验室规范判断实验室是否适合你。
最近动态
学习资料
发表论文
When do Models Generalize? A Perspective from Data-Algorithm Compatibility [arxiv]
Jing Xu* (许靖), Jiaye Teng* , Yang Yuan (袁洋), Andrew Chi-Chih Yao (姚期智)
Conference on Neural Information Processing Systems (NeurIPS) 2023
Finding Generalization Measures by Contrasting Signal and Noise [paper]
Jiaye Teng*, Bohang Zhang*(张博航), Ruichen Li*(李瑞晨), Haowei He*(何昊伟), Yequan Wang(王业全), Yan Tian(田燕), Yang Yuan(袁洋)
International Conference on Machine Learning (ICML) 2023
On Uni-Modal Feature Learning in Supervised Multi-Modal Learning [arxiv]
Chenzhuang Du*(杜晨壮), Jiaye Teng*, Tingle Li, Yichen Liu, Tianyuan Yuan, Yue Wang, Yang Yuan(袁洋), Hang Zhao(赵行)
International Conference on Machine Learning (ICML) 2023
Predictive Inference with Feature Conformal Prediction [arxiv]
Jiaye Teng*, Chuan Wen* (汶川), Dinghuai Zhang* (张鼎怀), Yoshua Bengio, Yang Gao (高阳), Yang Yuan (袁洋)
International Conference on Learning Representations (ICLR) 2023
Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models [arxiv] Kaiyue Wen* (温凯越), Jiaye Teng*, Jingzhao Zhang (张景昭)
International Conference on Learning Representations (ICLR) 2023
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming [arxiv] [paper]
Chuan Wen, Jianing Qian, Jierui Lin, Jiaye Teng, Dinesh Jayaraman, Yang Gao
International Conference on Machine Learning (ICML) 2022
Towards Understanding Generalization via Decomposing Excess Risk Dynamics [arxiv] [paper]
Jiaye Teng* , Jianhao Ma* (马鉴昊) , Yang Yuan (袁洋)
International Conference on Learning Representations (ICLR) 2022
Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis [arxiv]
Jiaye Teng* , Weiran Huang* (黄维然), Haowei He* (何昊伟)
International Conference on Artificial Intelligence and Statistics (AISTATS) 2022
T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP [arxiv] [paper]
Jiaye Teng* , Zeren Tan* (谭泽人), Yang Yuan (袁洋)
International Conference on Machine Learning (ICML) 2021
学术服务
- Workshop Organizer : BGPT @ICLR 2024
- Seminar Organizer: International Seminar on Foundational Artificial Intelligence (FAI-Seminar)
- Seminar Organizer: Foundations Of Data Science (FODS)
- Reviewer: ICML, NeurIPS, ICLR, AISTATS, T-PAMI
荣誉奖项
- 2024 清华大学优秀博士学位论文，清华大学
- 2024 清华大学优秀毕业生，清华大学
- 2023 王大中奖学金，清华大学
- 2022 国家奖学金，清华大学
- 2022 NeurIPS, Top Reviewer
- 2020 上海市优秀毕业生
- 2018 国家奖学金，上海财经大学