Algorithms and Theory

• Yueyang Liu, Xu Kuang, and Benjamin Van Roy, Non-Stationary Bandit Learning via Predictive Sampling, 2022.
  • Presented at INFORMS Annual Meeting 2022, MS&E Rising Stars Workshop 2023
  • A preliminary version appears in International Conference on Artificial Intelligence and Statistics (AISTATS) 2023
  • Major revision at Management Science
• Yueyang Liu, Xu Kuang, and Benjamin Van Roy, A Definition of Non-Stationary Bandits, 2023.
  • Presented at Stanford Data Science Conference 2023, SIAM Conference on Optimization 2023, Experimentation and Causal Inference in the Tech Sector Workshop 2023
  • To be submitted to Management Science
• Yueyang Liu, Adithya M. Devraj, Benjamin Van Roy, and Kuang Xu, Gaussian Imagination in Bandit Learning, 2022.
  • To be submmitted

Empirical and Applied Work

• Zheqing Zhu, Yueyang Liu, Kuang Xu, and Benjamin Van Roy, Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling, 2023.

Monograph

• Saurabh Kumar, Henrik Marklund, Ashish Rao, Yifan Zhu, Hong Jun Jeon, Yueyang Liu, Benjamin Van Roy, Continual Learning as Computationally Constrained Reinforcement Learning, 2023.
  • Under review at Foundations and Trends in Machine Learning