|
Eliza X. Y. Hu
Email  / 
Google Scholar  / 
Github
Hi, I am currently a Postdoctoral Associate at the Department of Data and Systems Engineering at the University of Hong Kong (HKU), supervised by Prof. Max Shen and Prof. Shaochong Lin.
Previously, I was a Postdoctoral Associate in the Department of Decisions, Operations and Technology at The Chinese University of Hong Kong (CUHK), supervised by Prof. Zhi Chen.
I received my Ph.D. in Computer Science and Engineering from CUHK, advised by Prof. Jimmy H. M. Lee.
My research lies at the intersection of AI and Optimization, focusing on developing machine learning methods for decision-making and solving complex real-world optimization problems.
I have published 10+ papers in top-tier conferences and journals, including oral and spotlight presentations, and serve as an Area Chair (AC) for ICLR and ICML.
My research spans:
|
|
-
Decision-Focused Learning (Predict+Optimize).
Developing learning frameworks that directly optimize downstream decision quality,
integrating machine learning with mathematical optimization under unknown objective
and constraint parameters, discrete decisions, and multi-stage information revelation.
-
Causal Learning and Decision Calibration.
Developing causal calibration methods that leverage limited experimental data and
observational information to improve prediction reliability under hidden confounding
and partial experimental coverage, and translate causal corrections into better
optimization decisions.
-
Exogenous-Aware Time Series Forecasting.
Developing data-driven forecasting methods that capture periodic patterns, external
events, and heterogeneous temporal dynamics, with applications to demand forecasting
and complex spatiotemporal systems.
-
Contextual and Stochastic Optimization.
Integrating contextual prediction with risk- and cost-aware optimization to support
resource allocation and operational decisions under demand uncertainty and asymmetric
business costs.
|
Major Publications
- Multi-Stage Predict+Optimize for Mixed Integer Linear Programs
[paper]
[supplement]
[code]
[video]
[poster]
Xinyi Hu, Jasper C. H. Lee, Jimmy H. M. Lee, Peter J. Stuckey
[NeurIPS 2024] Advances in Neural Information Processing Systems 37
- Two-Stage Predict+Optimize for MILPs with Unknown Parameters in Constraints
[paper]
[supplement]
[code]
[video]
[poster]
Xinyi Hu, Jasper C. H. Lee, Jimmy H. M. Lee
[NeurIPS 2023] Advances in Neural Information Processing Systems 36
- Branch & Learn with Post-hoc Correction for Predict+Optimize with Unknown Parameters in Constraints
[paper]
[arxiv]
[code]
[slides]
Xinyi Hu, Jasper C. H. Lee, Jimmy H. M. Lee
[CPAIOR 2023] Proceedings of the 20th International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research
- Predict+Optimize for Packing and Covering LPs with Unknown Parameters in Constraints
[paper]
[supplement]
[code]
[video]
[poster]
Xinyi Hu, Jasper C. H. Lee, Jimmy H. M. Lee
[AAAI 2023] Proceedings of the AAAI Conference on Artificial Intelligence (Oral)
- Branch & Learn for Recursively and Iteratively Solvable Problems in Predict+Optimize
[paper]
[supplement]
[code]
[video]
[poster]
Xinyi Hu, Jasper C. H. Lee, Jimmy H. M. Lee, Allen Z. Zhong
[NeurIPS 2022] Advances in Neural Information Processing Systems 35
Other Publications
- BlockEdge: A Hybrid Blockchain Framework for Secure and Efficient Collaboration in EEC Environments
Wangbo Shen, Weiwei Lin, Tiansheng Huang, Xinyi Hu, Mian Guo, Haijie Wu
[TOIT 2025] ACM Transactions on Internet Technology
- CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
[paper]
[code]
[video]
[poster]
Shengsheng Lin, Weiwei Lin, Xinyi Hu, Wentai Wu, Ruichao Mo, Haocheng Zhong
[NeurIPS 2024] Advances in Neural Information Processing Systems 37 (Spotlight)
- Correctional Regret for Predict+Optimize with Unknown Objectives and Constraints
[paper]
[slides]
Xinyi Hu, Jasper C. H. Lee, Jimmy H. M. Lee, Allen Z. Zhong
[IJCAI 2022] IJCAI 2022 DSO Workshop: Data Science meets Optimisation
- Video Server Deployment Using a Genetic Algorithm with Deterministic Initialization Strategy
[paper]
Xinyi Hu, Yue-Jiao Gong, Xin-Yuan Zhang, Yi-Ning Ma, Jun Zhang
[ISNN 2018] International Symposium on Neural Networks
- Intelligent video content server deployment method and system
[Patent] China Invention Grant (No. CN108616401B), 2018
Selected Awards
- Student Stipends, CPAIOR, 2023
- Student Scholarship and Volunteer Program, AAAI, 2023
- Scholar Award, NeurIPS, 2022 & 2023
- Leader of Excellent Project of the National Undergraduate Innovation and Entrepreneurship Training Program, Ministry of Education of China, 2018
- National Scholarship (highest honor in China), Ministry of Education of China, 2017 & 2016
- National Second prize, First prize in Guangdong Province in CUMCM (China Undergraduate Mathematical Contest in Modeling), China Society for Industrial and Applied Mathematics, 2017
Teaching Experience
Teaching Assistant
- CSCI3180: Principles of Programming Languages, 2020 Spring/2021 Spring/2022 Spring, CUHK
- CSCI1540: Fundamental Computing with C++, 2019 Fall/2020 Fall, CUHK
- ENGG1003: Digital Literacy and Computational Thinking, 2021 Fall/2022 Spring, CUHK
Thanks to Jon Barron for sharing the code of his personal webpage.
|
|