working papers and publications in reversed chronological order.


  1. Preprint
    Learning Variational Inequalities: Generalization Bounds and Applications to Empirical Games
    Eric Zhao, Tatjana Chavdarova, and Michael I. Jordan
    Working paper, last update: Dec 2022. (Preprint)
    Dec 2022
  2. Neurips 2022
    On-Demand Sampling: Learning Optimally from Multiple Distributions
    Nika Haghtalab, Michael Jordan, and Eric Zhao* Alphabetically ordered author names.
    In Proceedings of the 35th Annual Conference on Neural Information Processing Systems. (Neurips 2022)
    May 2022
    Oral presentation (Top 2% of accepted papers).
  3. Scaling Bias Mitigation with Multiple Fairness Tasks and Multiple Protected Attributes
    Eric Zhao, De-An Huang, Hao Liu, Zhiding Yu, Anqi Liu, Olga Russakovsky, and Anima Anandkumar
    Working paper, last update: May 2022. (Preprint)
    May 2022


  1. Learning to Play General-Sum Games Against Multiple Boundedly Rational Agents
    Eric Zhao, Alexander R. Trott, Caiming Xiong, and Stephan Zheng
    In Proceedings of the 37th AAAI Conference on Artificial Intelligence. (AAAI 2023)
    Jun 2021
  2. Active Learning under Label Shift
    Eric Zhao, Anqi Liu, Animashree Anandkumar, and Yisong Yue
    In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics. (AISTATS 2021)
    Feb 2021