Rong Ge, Cue Family Associate Professor of Computer Science

Theoretical computer science and machine learning.

Contact Info:

Office Location:
Email Address:
Web Page:	https://users.cs.duke.edu/~rongge/

Teaching (Fall 2024):

• COMPSCI 701S.01, INTRO GRAD STUDENTS COMPSCI Synopsis

  LSRC D106, F 01:25 PM-02:40 PM

Education:

Ph.D.

Princeton University

2013

Recent Publications   (More Publications)

1. Chidambaram, M; Wu, C; Cheng, Y; Ge, R, Hiding Data Helps: On the Benefits of Masking for Sparse Coding, Proceedings of Machine Learning Research, vol. 202 (January, 2023), pp. 5600-5615  [abs]
2. Zhou, M; Ge, R, Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression, Proceedings of Machine Learning Research, vol. 202 (January, 2023), pp. 42543-42573  [abs]
3. Wu, C; Li, LE; Ermon, S; Haffner, P; Ge, R; Zhang, Z, The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models, Proceedings of Machine Learning Research, vol. 239 (January, 2023), pp. 118-126  [abs]
4. Chidambaram, M; Wang, X; Wu, C; Ge, R, Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup, Proceedings of Machine Learning Research, vol. 202 (January, 2023), pp. 5563-5599  [abs]
5. Zhao, H; Panigrahi, A; Ge, R; Arora, S, Do Transformers Parse while Predicting the Masked Word?, EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings (January, 2023), pp. 16513-16542, ISBN 9798891760608  [abs]

Recent Grant Support

• Collaborative Reseach: Transferable, Hierarchical, Expressive, Optimal, Robust, Interpretable NETworks (THEORINET), National Science Foundation, 2020/09-2025/08.      
• Collaborative Reseach: Transferable, Hierarchical, Expressive, Optimal, Robust, Interpretable NETworks (THEORINET), Simons Foundation, 2020/09-2025/08.      
• CAREER: Optimization Landscape for Non-convex Functions - Towards Provable Algorithms for Neural Networks, National Science Foundation, 2019/07-2024/06.      
• HDR TRIPODS: Innovations in Data Science: Integrating Stochastic Modeling, Data Representation, and Algorithms, National Science Foundation, 2019/10-2023/09.      
• Ge Sloan Fellowship 2019, Alfred P. Sloan Foundation, 2019/09-2023/09.      
• AF:Large:Collaborative Research:Nonconvex methods and models for learning: Towards algorithms with provable and interpretable guarantees, National Science Foundation, 1704656, 2017/06-2022/05.