Yingce Xia (夏应策)

alt text 

I am currently a final-year PhD student in School of Information Science and Technology, University of Science and Technology of China (USTC). I'm in a joint PhD program between University of Science and Technology of China and Microsoft Research Asia (MSRA) . I am very fortunate to be supervised by Dr. Tie-Yan Liu and Prof. Nenghai Yu. Prior to that, I obtained my bachalor degree from Department of Information Security, USTC in June, 2013.

My research revolves around dual learning (a new learning paradigm proposed by our group), deep reinforcement learning (with application to neural machine translation), distributed machine learning (with application to efficient data parallel machanism) and bandit algorithms (with special interests in budgeted MABs). I am also interested in game/auction theory.

My Curriculum Vitae is here.

Publications

Journal & Conference Papers

  • Yingce Xia, Xu Tan, Fei Tian, Tao Qin, Nenghai Yu and Tie-Yan Liu, Model-Level Dual Learning, 35th International Conference on Machine Learning (ICML-18).

  • Haifang Li, Yingce Xia and Wensheng Zhang, Finite Sample Analysis of LSTD with Random Projections and Eligibility Trace, 27th International Joint Conference on Artificial Intelligence (IJCAI-18).

  • Jianxin Lin, Yingce Xia, Tao Qin, Zhibo Chen and Tie-Yan Liu, Conditional Image-to-Image Translation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR-18).

  • Yijun Wang, Yingce Xia, Li Zhao, Jiang Bian, Tao Qin, Guiquan Liu and Tie-Yan Liu, Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization, In 32nd AAAI Conference on Artificial Intelligence (AAAI-18).

  • Yingce Xia, Fei Tian, Lijun Wu, Jianxin Lin, Tao Qin, Nenghai Yu and Tie-Yan Liu, Deliberation Networks: Sequence Generation Beyond One-Pass Decoding, In 31th Conference on Neural Information Processing Systems (NIPS-17).

  • Di He, Hanqing Lu, Yingce Xia, Tao Qin, Liwei Wang and Tie-Yan Liu, Decoding with Value Networks for Neural Machine Translation, In 31th Conference on Neural Information Processing Systems (NIPS-17).

  • Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu and Tie-Yan Liu, Dual Supervised Learning, In 34th International Conference on Machine Learning, (ICML-2017). [pdf]

  • Yingce Xia, Jiang Bian, Tao Qin, Nenghai Yu and Tie-Yan Liu, Dual Inference for Machine Learning, In 26th International Joint Conference on Artificial Intelligence, (IJCAI-2017). [pdf]

  • Yingce Xia, Fei Tian, Tao Qin, Nenghai Yu and Tie-Yan Liu, Sequence Generation with Target Attention, In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017, (ECML/PKDD-2017).

  • Yingce Xia, Tao Qin, Wenkui Ding, Haifang Li, Xu-Dong Zhang, Nenghai Yu and Tie-Yan Liu, Finite Budget Analysis of Multi-armed Bandit Problems, (Neurocomputing 2017). [pdf]

  • Haifang Li, Yingce Xia, Infinitely Many-Armed Bandits with Budget Constraints, In 31st AAAI Conference on Artificial Intelligence (AAAI-17). [Full Version]

  • Di He*, Yingce Xia*, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu and Wei-Ying Ma, Dual Learning for Machine Translation, In 30th Conference on Neural Information Processing Systems (NIPS-16). ("*" indicates equal contribution.) [arXiv]

  • Yingce Xia, Tao Qin, Weidong Ma, Nenghai Yu and Tie-Yan Liu, Budgeted Multi-armed Bandits with Multiple Plays, In 25th International Joint Conference on Artificial Intelligence (IJCAI-16). [Full Version]

  • Yingce Xia, Tao Qin, Nenghai Yu and Tie-Yan Liu, Best Action Selection in a Stochastic Environment,In 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-16). [pdf]

  • Yingce Xia, Wenkui Ding, Xu-Dong Zhang, Nenghai Yu and Tao Qin, Budgeted Bandit Problems with Continuous Random Costs, In 7th Asian Conference on Machine Learning (ACML-15). [pdf]

  • Yingce Xia, Haifang Li, Tao Qin, Nenghai Yu and Tie-Yan Liu, Thompson Sampling for Budgeted Multi-armed Bandits, In 24th International Joint Conference on Artificial Intelligence (IJCAI-15). [pdf] [Full Version]

  • Long Tran–Thanh, Yingce Xia, Tao Qin and Nicholas R. Jennings, Efficient Algorithms with Performance Guarantees for the Stochastic Multiple-Choice Knapsack Problem, In 24th International Joint Conference on Artificial Intelligence (IJCAI-15). [pdf]

  • Yingce Xia, Tao Qin, Nenghai Yu and Tie-Yan Liu, Incentivizing High-quality Content from Heterogeneous Users: On the Existence of Nash Equilibrium, In 28th AAAI Conference on Artificial Intelligence (AAAI-14). [pdf]

Preprints

  • Lijun Wu, Yingce Xia, Li Zhao, Fei Tian, Tao Qin, Jianhuang Lai and Tie-Yan Liu, Adversarial Neural Machine Translation, Draft, 2017. [pdf]

  • Yingce Xia, Tao Qin, Nenghai Yu and Tie-Yan Liu, Incentivizing High-Quality Content from Hetergeneous Users, Draft, 2015. [pdf]



Awards

  • National Scholarship 2017
  • MSRA PhD Fellowship 2016


Contact

Tower 2, Microsoft Research Asia
No. 5, Danling Street, Haidian District, Beijing, P.R. China

Email: yingce.xia@gmail.com, xiayingc@mail.ustc.edu.cn

Personal Page: http://home.ustc.edu.cn/~xiayingc