About Me

Hi there, my name is Ruiquan Huang (pronounced ‘Ray-chwen Hwang’, you are also welcome to call me Ray). I am a Ph.D. candidate at The Pennsylvania State University, and am fortunate to be advised by Professor Jing Yang. Prior to that, I received my B.S. from the University of Science and Technology of China (USTC), and M.S. degrees from Columbia University.

• Email: rzh 55 14 at psu dot edu
• LinkedIn: Ruiquan Huang

My research interests lie in broad areas, ranging from reinforcement learning (RL) and bandits to statistical learning theory and deep learning. The ultimate goal is to advance machine learning (ML) and develop provable yet practically efficient and trustworthy machine learning algorithms.

• Efficiency: (1) statistical efficiency, (2) computational efficiency,
• Trustowrhiness: (1) safety, (2) privacy, (3) robustness.

Selected Publications (Full list)

• Non-asymptotic Convergence of Training Transformers for Next-token Prediction,
  R. Huang, Y. Liang, J. Yang, NeurIPS 2024.
• Provably Efficient UCB-type Algorithms For Learning Predictive State Representations,
  R. Huang, Y. Liang, J. Yang, ICLR 2024.
• Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL,
  R. Huang, J. Yang, Y. Liang, ICLR 2023.
• Federated Linear Contextual Bandits with User-level Differential Privacy,
  R.Huang, H. Zhang, L. Melis, M. Shen, M. Hejazinia, J. Yang, ICML 2023.
• Federated Linear Contextual Bandits,
  R. Huang, W. Wu, J. Yang, C. Shen, NeurIPS 2021.

Awards

• Future Faculty Immersive Teaching (FIT) Fellow at PSU, 2023-2024.
• Melvin P. Bloom Memorial Graduate Fellowship in Electrical Engineering at PSU, 2024.
• Joab and Marly Thomas Graduate Fellowship, PSU 2024-2025.

Teaching

Instructor of EDSGN 100, Fall 2023, Spring 2024.

Service

• Conference reviewer: Neurips, ICML, ICLR, AAAI, AISTATS