About Me
I am a Computer Science PhD student in University of Southern California. I am very fortunate to be advised by Prof. Haipeng LuoBefore coming to USC, I worked as a research assistant in Academia Sinica, where I spent great time working with Prof. Chi-Jen Lu and my colleagues on several online learning problems. Prior to studying machine learning, I studied wireless network technologies, and got my master's degree from National Taiwan University. My advisor was Prof. Wanjiun Liao.  My CV can be found here

My email is chenyu dot wei at usc dot edu.


Research
Recently I work on several bandit problems, including multi-armed bandits, contextual bandits, and bandit classification. In general, I am interested in designing algorithms (especially in online learning and reinforcement learning), and formalizing their theoretical guarantees. 


Papers 
  • Yifang Chen, Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei
    A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free  [arXiv]
    Preprint. 

  • Sébastien Bubeck, Yuanzhi Li, Haipeng Luo, Chen-Yu Wei
    Improved Path-length Regret Bounds for Bandits  [arXiv]
    Preprint. 

  • Alina Beygelzimer, Dávid Pál, Balázs Szörényi, Devanathan Thiruvenkatachari, Chen-Yu Wei, Chicheng Zhang
    Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case  [arXiv]
    Preprint. 

  • Julian Zimmert, Haipeng Luo, Chen-Yu Wei
    Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously  [arXiv]
    Preprint. 
     
  • Haipeng Luo, Chen-Yu Wei, Kai Zheng
    Efficient Online Portfolio with Logarithmic Regret  [arXiv]
    Advances in Neural Information Processing Systems (NIPS) 2018.  

  • Haipeng Luo, Chen-Yu Wei, Alekh Agarwal, John Langford 
    Efficient Contextual Bandits in Non-stationary Worlds  [arXiv]
    Computational Learning Theory (COLT), 2018.  

  • Chen-Yu Wei and Haipeng Luo 
    More Adaptive Algorithms for Adversarial Bandits  [arXiv]
    Computational Learning Theory (COLT), 2018. 

  • Chen-Yu Wei, Yi-Te Hong, and Chi-Jen Lu 
    Online Reinforcement Learning in Stochastic Games  [arXiv]
    Advances in Neural Information Processing Systems (NIPS) 2017.  

  • Chen-Yu Wei, Yi-Te Hong, and Chi-Jen Lu 
    Tracking the Best Expert in Non-stationary Stochastic Environments  [arXiv]
    Advances in Neural Information Processing Systems (NIPS) 2016.  
(Wireless Networks)
  • Chen-Yu Wei and Wanjiun Liao 
    Multi-Cell Cooperative Scheduling for Network Utility Maximization With User Equipment Side Interference Cancellation  [IEEE Xplore]
    IEEE Transactions on Wireless Communications, vol.17, no.1, pp.619-635, Jan. 2018.  

  • Hsu Kao, Chen-Yu Wei, Hsiao-Ching Lin, Yi-Han Chiang, and Wanjiun Liao
    Adaptive Measurement for Energy Efficient Mobility Management in Ultra-dense Small Cell Networks  [IEEE Xplore] 
    IEEE International Conference on Communications (ICC), 2016