Jincheng Mei   Ph.D. Candidate Department of Computing Science University of Alberta Edmonton, Alberta Canada, T6G 2E8 Email: jmei2 AT ualberta.ca

Bio

I am a Ph.D. candidate. My supervisor is Dale Schuurmans. I am now doing research in the area of machine learning, reinforcement learning, and optimization. I received my M.S. degree from Shanghai Jiao Tong University in 2015. Before that, I received my B.E. degree from South China University of Technology in 2012.

Experiences

• 2019.08 - Present: Student Researcher, Google Brain.
  
• 2018.09 - 2019.05: Research Intern, Borealis AI Lab.
  

Papers

* indicates equal contribution.

• Leveraging Non-uniformity in First-order Non-convex Optimization.
  Jincheng Mei*, Yue Gao*, Bo Dai, Csaba Szepesvári, and Dale Schuurmans.
  International Conference on Machine Learning (ICML), 2021.
  

  [arXiv]

• On the Optimality of Batch Policy Optimization Algorithms.
  Chenjun Xiao*, Yifan Wu*, Tor Lattimore, Bo Dai, Jincheng Mei, Lihong Li, Csaba Szepesvári, and Dale Schuurmans.
  International Conference on Machine Learning (ICML), 2021.
  

  [arXiv]

• Beyond Prioritized Replay: Sampling States in Model-Based Reinforcement Learning via Simulated Priorities.
  Jincheng Mei*, Yangchen Pan*, Amir-massoud Farahmand, Hengshuai Yao, and Martha White.
  Preprint, 2020.
  

  [arXiv]

• Escaping the Gravitational Pull of Softmax.
  Jincheng Mei, Chenjun Xiao, Bo Dai, Lihong Li, Csaba Szepesvári, and Dale Schuurmans.
  Advances in Neural Information Processing Systems (NeurIPS), 2020.
  Oral Presentation
  

  [Paper]

• On the Global Convergence Rates of Softmax Policy Gradient Methods.
  Jincheng Mei, Chenjun Xiao, Csaba Szepesvári, and Dale Schuurmans.
  International Conference on Machine Learning (ICML), 2020.
  

  [Paper][arXiv]

• Frequency-based Search-control in Dyna.
  Yangchen Pan*, Jincheng Mei*, and Amir-massoud Farahmand.
  International Conference on Learning Representations (ICLR), 2020.
  

  [Paper]

• Maximum Entropy Monte-Carlo Planning.
  Chenjun Xiao, Jincheng Mei, Ruitong Huang, Dale Schuurmans, and Martin Müller.
  Advances in Neural Information Processing Systems (NeurIPS), 2019.
  

  [Paper]

• On Principled Entropy Exploration in Policy Optimization.
  Jincheng Mei*, Chenjun Xiao*, Ruitong Huang, Dale Schuurmans, and Martin Müller.
  International Joint Conference on Artificial Intelligence (IJCAI), 2019.
  

  [Paper][Long version]

• Memory-Augmented Monte Carlo Tree Search.
  Chenjun Xiao, Jincheng Mei, and Martin Müller.
  AAAI Conference on Artificial Intelligence (AAAI), 2018.
  Outstanding Paper Award
  

  [Paper]

• Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters.
  Min Yang, Jincheng Mei, Heng Ji, Wei Zhao, Zhou Zhao, and Xiaojun Chen.
  International Conference on Empirical Methods in Natural Language Processinge (EMNLP), 2017.
  

  [Paper]

• Discovering Author Interest Evolution in Topic Modeling.
  Min Yang, Jincheng Mei, Fei Xu, Wenting Tu, and Ziyu Lu.
  International ACM SIGIR conference on Research and Development in Information Retrieval (SIGIR), 2016.
  

  [Paper]

• On the Reducibility of Submodular Functions.
  Jincheng Mei, Hao Zhang, and Bao-Liang Lu.
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.
  

  [Paper]

• On Unconstrained Quasi-Submodular Function Optimization.
  Jincheng Mei, Kang Zhao, and Bao-Liang Lu.
  AAAI Conference on Artificial Intelligence (AAAI), 2015.
  

  [Paper]

• Locality Preserving Hashing.
  Kang Zhao, Hongtao Lu, and Jincheng Mei.
  AAAI Conference on Artificial Intelligence (AAAI), 2014.
  

  [Paper]

• Saliency Level Set Evolution.
  Jincheng Mei and Bao-Liang Lu.
  International Conference on Neural Information Processing (ICONIP), 2014.
  

  [Paper]