Renzhe Xu   徐韧喆

Ph.D. Candidate at Tsinghua University
Email: xrz199721 [at] gmail [dot] com
Curriculum Vitae (2024.02)

profile.png

Hi! I am a fifth year PhD student in Computer Science and Technology at Tsinghua University, where I obtained a bachelor’s degree in Computer Science and Technology in 2019. I conduct research under the supervision of Prof. Peng Cui and Prof. Bo Li. Currently, I am visiting the Theory Group at the Department of Computer Science, Duke University, working with Prof. Kamesh Munagala during the Spring Semester of 2024.

My research focuses on algorithm governance in decision-making systems, ensuring they can be trusted in practical applications. My key areas of interest include:

  • Algorithm governance for decision-making models
    • Personalized pricing algorithms and price discrimination
    • Recommendation algorithms and information cocoon
  • Algorithm governance for predictive models from biased data
    • Out-of-distribution generalization
    • Algorithmic fairness

Selected publications

The full list of publications can be found in the publications page.
* indicates equal contributions.

Algorithm Governance for Decision-making Models

  1. Competing for Shareable Arms in Multi-Player Multi-Armed Bandits
    Renzhe Xu*, Haotian Wang*, Xingxuan Zhang, Bo Li, and Peng Cui
    In Proceedings of the 40th International Conference on Machine Learning (ICML 2023)
    Code
  2. Product Ranking for Revenue Maximization with Multiple Purchases
    Renzhe Xu, Xingxuan Zhang, Bo Li, Yafeng Zhang, Xiaolong Chen, and Peng Cui
    In Advances in Neural Information Processing Systems (NeurIPS 2022)
    Code
  3. Regulatory Instruments for Fair Personalized Pricing
    Renzhe Xu, Xingxuan Zhang, Peng Cui, Bo Li, Zheyan Shen, and Jiazheng Xu
    In Proceedings of the ACM Web Conference 2022 (WWW 2022)
    Code Scientific American Montreal AI Ethics Institute

Algorithm Governance for Predictive Models from Biased Data

  1. Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization
    Xingxuan Zhang*, Renzhe Xu*, Han Yu, Hao Zou, and Peng Cui
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
    Highlights (2.6%)
    Code
  2. A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization
    Renzhe Xu, Xingxuan Zhang, Zheyan Shen, Tong Zhang, and Peng Cui
    In Proceedings of the 39th International Conference on Machine Learning (ICML 2022)
    Code
  3. Algorithmic Decision Making with Conditional Fairness
    Renzhe Xu, Peng Cui, Kun Kuang, Bo Li, Linjun Zhou, Zheyan Shen, and Wei Cui
    In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2020)
    Code

Teaching

  • 2020, 2021 spring: TA in Big Data Analytics (B), instructed by Prof. Peng Cui.
  • 2021 fall: TA in Big Data Analytics (B), instructed by Prof. Wenwu Zhu and Prof. Peng Cui.

Services

  • Top reviewer: NeurIPS 2022 (10%)
  • Conference reviewer / Program committee: ICML (2022-2024), ICLR (2023-2024), NeurIPS (2022-2023), UAI (2022-2024), CVPR (2022-2024), ICCV (2023), ECCV (2022, 2024), KDD (2022-2024), WWW (2024), FAccT (2024), CLeaR (2024), AAAI (2022)
  • Contributor of IEEE Standards Association 3198 Development Group - Standard for Evaluation Method of Machine Learning Fairness
Acknowledgments: based on Jekyll with al-folio theme by Maruan Al-Shedivat.