Boxiang Lyu

Boxiang Lyu

PhD (2019-2024)
University of Chicago Booth School of Business

Boxiang Lyu was a PhD student in the Econometrics and Statistics dissertation area at University of Chicago Booth School of Business. Prior to Booth, he obtained a Master of Science in Machine Learning (2019) and a Bachelor of Science in Statistics and Machine Learning (2018) from Carnegie Mellon University.

Personal website

Interests

  • optimization
  • machine learning

Education

  • MS in Machine Learning, 2019
    Carnegie Mellon University
  • BS in Statistics and Machine Learning, 2018
    Carnegie Mellon University

Publications

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning
Dake Zhang, Boxiang Lyu, Shuang Qiu, Mladen Kolar, Tong Zhang
International Conference on Machine Learning (ICML)
Preprint
One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning
Pedro Cisneros Velarde, Boxiang Lyu, Sanmi Koyejo, Mladen Kolar
International Conference on Artificial Intelligence and Statistics (AISTATS)
arXiv URL
L-SVRG and L-Katyusha with Adaptive Sampling
Boxin Zhao, Boxiang Lyu, Mladen Kolar
Transactions on Machine Learning Research
arXiv
Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
Boxin Zhao, Boxiang Lyu, Raul Castro Fernandez, Mladen Kolar
International Conference on Machine Learning (ICML)
Preprint DOI
Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
Boxiang Lyu, Zhaoran Wang, Mladen Kolar, Zhuoran Yang
Proceedings of the 39th International Conference on Machine Learning (ICML) 2022
PDF Video Slides arXiv
Personalized Federated Learning with Multiple Known Clusters
Boxiang Lyu, Filip Hanzely, Mladen Kolar
Technical report (arXiv:2204.13619)
arXiv