Boxin Zhao

Boxin Zhao

PhD (2020-2025)
University of Chicago Booth School of Business

Boxin Zhao was a PhD student in Econometrics and Statistics at University of Chicago, Booth School of Business. His research interests include probabilistic graphical models, functional data analysis and distributed learning, with a focus on developing novel methodologies with both practical applications and theoretical guarantees.

Personal website

Interests

  • Machine learning
  • Probabilistic graphical models
  • Functional data analysis
  • Distributed learning
  • High-dimensional statistics

Education

  • PhD in Econometrics and Statistics, 2025
    University of Chicago Booth School of Business
  • MS in Statistics, 2020
    University of Chicago
  • BS in Statistics, 2018
    Nankai University

Publications

Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimation
Boxin Zhao, Cong Ma, Mladen Kolar
Journal of the American Statistical Association
Preprint DOI
SMART: A Spectral Transfer Approach to Multi-Task Learning
Boxin Zhao, Mladen Kolar, Jinchi Lv
Technical report
Preprint
Provable Accelerated Bayesian Optimization with Knowledge Transfer
Haitao Lin, Boxin Zhao, Mladen Kolar, Chong Liu
International Conference on Artificial Intelligence and Statistics (AISTATS)
Preprint DOI
Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback
Boxin Zhao, Ziqi Liu, Chaochao Chen, Mladen Kolar, Zhiqiang Zhang, Jun Zhou
Journal of Machine Learning Research, 26(8), 1–67
Preprint
Personalized Binomial DAGs Learning with Network Structured Covariates
Boxin Zhao, Weishi Wang, Dingyuan Zhu, Ziqi Liu, Dong Wang, Zhiqiang Zhang, Jun Zhou, Mladen Kolar
Technical report
Preprint
Latent Multimodal Functional Graphical Model Estimation
Katherine Tsai, Boxin Zhao, Oluwasanmi Koyejo, Mladen Kolar
Journal of the American Statistical Association, 119(547), 2217–2229
arXiv DOI
High-dimensional Functional Graphical Model Structure Learning via Neighborhood Selection Approach
Boxin Zhao, Percy Zhai, Y. Samuel Wang, Mladen Kolar
Electronic Journal of Statistics, 18(1), 1042–1129
Preprint DOI
Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
Filip Hanzely, Boxin Zhao, Mladen Kolar
Transactions on Machine Learning Research
Preprint Code Video Poster
L-SVRG and L-Katyusha with Adaptive Sampling
Boxin Zhao, Boxiang Lyu, Mladen Kolar
Transactions on Machine Learning Research
arXiv
Differentially Private Matrix Completion through Low-rank Matrix Factorization
Lingxiao Wang, Boxin Zhao, Mladen Kolar
International Conference on Artificial Intelligence and Statistics (AISTATS)
URL
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
FuDGE: A Method to Estimate a Functional Differential Graph in a High-Dimensional Setting
Boxin Zhao, Y. Samuel Wang, Mladen Kolar
Journal of Machine Learning Research
arXiv Code URL
Direct Estimation of Differential Functional Graphical Models
Boxin Zhao, Y. Samuel Wang, Mladen Kolar
Advances in Neural Information Processing Systems, 32
PDF