Publications

Peer Reviewed Conference

  • Reward Shaping via Meta-Learning [arXiv]
    Haosheng Zou*, Tongzheng Ren*, Dong Yan, Hang Su, Jun Zhu (* Equal Contribution)
    AAAI Conference on Artificial Intelligence (AAAI) 2021

  • Stein Self-Repulsive Dynamics: Benefits from Past Samples. [arXiv] [NeurIPS version]
    Mao Ye*, Tongzheng Ren*, Qiang Liu (* Equal Contribution)
    Advances in Neural Information Processing Systems (NeurIPS) 2020

  • Implicit Regularization and Convergence for Weight Normalization. [arXiv] [NeurIPS version]
    Xiaoxia Wu*, Edgar Dobriban*, Tongzheng Ren*, Shanshan Wu*, Zhiyuan Li, Suriya Gunasekar, Rachel Ward, Qiang Liu (* Equal Contribution)
    Advances in Neural Information Processing Systems (NeurIPS) 2020

  • Accountable Off-Policy Evaluation via a Kernelized Bellman Statistics. [arXiv] [ICML version]
    Yihao Feng*, Tongzheng Ren*, Ziyang Tang*, Qiang Liu (* Equal Contribution)
    International Conference on Machine Learning (ICML) 2020

  • Exploration Analysis in Finite-Horizon Turn-based Stochastic Games. [UAI version]
    Jialian Li, Yichi Zhou, Tongzheng Ren, Jun Zhu
    Conference on Uncertainty in Artificial Intelligence (UAI) 2020.

  • Lazy-CFR: a fast regret minimization algorithm for extensive games with imperfect information. [arXiv] [ICLR version]
    Yichi Zhou, Tongzheng Ren, Jialian Li, Dong Yan, Jun Zhu
    International Conference on Learning Representation (ICLR) 2020

  • Learn a Robust Policy in Adversarial Games via Playing with an Expert Opponent. [AAMAS version]
    Jialian Li, Tongzheng Ren, Hang Su, Jun Zhu
    International Conference on Autonomous Agents and MultiAgent Systems (AAMAS) 2019 (Extended Abstract)

  • Function Space Particle Optimization for Bayesian Neural Networks. [arXiv] [ICLR version]
    Ziyu Wang, Tongzheng Ren, Jun Zhu, Bo Zhang
    International Conference on Learning Representation (ICLR) 2019

  • Learning to write stylized Chinese Charaters by Reading a Handful of Examples. [arXiv] [IJCAI version]
    Danyang Sun*. Tongzheng Ren*, Chongxuan Li, Hang Su, Jun Zhu (* Equal Contribution)
    International Joint Conference on Artificial Intelligence (IJCAI) 2018

Preprint

  • MaxUp: A Simple Way to Improve Generalization of Neural Network Training [arXiv]
    Chengyue Gong*, Tongzheng Ren*, Mao Ye, Qiang Liu (* Equal Contribution)