About me
Hi there! I’m Ryan, a final-year Ph.D. student in Information Systems Management at Heinz College, Carnegie Mellon University, advised by Woody Zhu and Ramteen Sioshansi. My research develops machine learning and optimization methods for decision-making under uncertainty, with applications to power-system resilience against wildfires and extreme weather.
I am on the 2026–2027 academic job market. CV (PDF)
My work trains predictive models for the decisions they inform (decision-focused learning) and builds uncertainty sets with statistical guarantees into robust and chance-constrained optimization. Specifically:
- Decision-focused learning: generative and neural ODE models trained on decision quality rather than forecast accuracy (ICLR 2026, IEEE Trans. Smart Grid).
- Robust optimization with conformal guarantees: uncertainty sets that are statistically valid and shaped by the downstream decision (NeurIPS 2026).
- Wildfire and extreme-weather resilience: planning and operating large power systems under rare, high-impact hazards (INFORMS ENRE Best Student Paper, wildfire planning, public platform).
Before my Ph.D., I earned a Master’s degree in Information Systems Management from CMU and a B.B.A. in Supply Chain and Logistics Management from the Chinese University of Hong Kong (Shenzhen), and worked as a data scientist at ByteDance.
Teaching: Lecturer, A/B Testing (95-819), Heinz College, Carnegie Mellon University, 2026.
📣 News
- Oct 2026: Presented our work on rare-chance-constrained resilience planning under wildfires and cascading hazards at the Young Researchers Workshop at Cornell University. Thank you to the organizers for organizing such a wonderful event!
- Sept 2026: Our paper on balancing planning myopia and forecast error has been selected as INFORMS DMDA Workshop 2026 Finalist (Applied Track).
- Sept 2026: Presented our paper on wildfire resilience planning at HOPE Research Workshop hosted by HOPE Lab. Thank you to all the organizers for the invitation and for hosting the workshop!
- Sept 2026: Excited to release our wildfire analytics website that allows real-time data analysis, interactive QA chatbot, and data download. Feel free to try it out!
- Sept 2026: Our paper on conformal set modeling for contextual robust optimization has been accepted by NeurIPS 2026.
- May 2026: Won the IISE DAIS Best Track Paper Competition with our [paper]. I am grateful to my advisor Woody and Prof. Nando Fioretto and all of my amazing coauthors.
- Oct 2025: Won the INFORMS ENRE Best Student Paper Award with our [paper] on robust optimization for power system resilience. Grateful to Woody and Ramteen for their guidance!
- Sept 2025: Co-chairing the INFORMS DMDA workshop 2025 Data Challenge on high-frequency outage prediction.
- Aug 2025: Attended KDD 2025 Toronto and presented our [paper] on counterfactual fairness.
- May 2025: Attended NSF Workshop on Uncertainty Quantification and Machine Learning for Complex Physical Systems, Chicago. Presented a poster for our [paper].
- Oct 2024: Presented two working papers [1] [2] at INFORMS Workshop on Data Science and Workshop on Data Mining and Decision Analytics.
- Aug 2024: Awarded the INFORMS Student Scholarship by the INFORMS Workshop on Data Science 2024 Program Committee.
Show moreShow less
📄 Journal Publications
Shuyi Chen, Ferdinando Fioretto, Feng Qiu, and Shixiang Zhu. Global-Decision-Focused Neural ODEs for Proactive Grid Resilience Management. IEEE Transactions on Smart Grid. [arXiv] [poster] [code]
📑 Peer-Reviewed Conference Proceedings
Shuyi Chen*, Wenbin Zhou*, and Shixiang Zhu. Learning Polyhedral Conformal Sets for Contextual Robust Optimization. Conference on Neural Information Processing Systems (NeurIPS), 2026. [arXiv]
Prince Zizhuang Wang, Shuyi Chen, Jinhao Liang, Ferdinando Fioretto, and Shixiang Zhu. Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making. International Conference on Learning Representations (ICLR), 2026. [arXiv]
🏆 IISE DAIS Track Best Paper AwardShuyi Chen and Shixiang Zhu. Counterfactual Fairness through Transforming Data Orthogonal to Bias. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Research Track, 2025. [arXiv] [code]
Shuyi Chen, Kaize Ding, and Shixiang Zhu. Uncertainty-Aware Robust Learning on Noisy Graphs. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. [arXiv] [poster] [code]
A short version was accepted by the New Frontiers in Graph Learning Workshop at NeurIPS 2023.Yihan Cao*, Shuyi Chen*, Ryan Liu*, Zhiruo Wang, and Daniel Fried. API-Assisted Code Generation for Question Answering on Varied Table Structures. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023. [arXiv]
🔬 Working Papers
Shuyi Chen, Shixiang Zhu, and Ramteen Sioshansi. Enhancing Electricity-System Resilience with Adaptive Robust Optimization and Conformal Uncertainty Characterization. Minor revision at IEEE Open Access Journal of Power and Energy. [arXiv] [poster] [news]
🏆 INFORMS ENRE Best Student Paper AwardShuyi Chen, Shixiang Zhu, and Ramteen Sioshansi. Large-Scale Resilience Planning for Wildfire-Prone Electricity Systems via Adaptive Robust Optimization. To be submitted to European Journal of Operational Research. [arXiv] [poster] [demo]
Shuyi Chen, Shuai Wang, and Shixiang Zhu. The Price of Looking Ahead: Decision-Focused Learning for Model Predictive Control in Energy Storage. In preparation for conference submission. Earlier version: “Balancing Planning Myopia and Forecast Error: Decision-Focused Sequential Learning.”
🏆 INFORMS DMDA Workshop Best Paper Finalist (Applied Track)Shuyi Chen, Shixiang Zhu, and Ramteen Sioshansi. Rare-Chance-Constrained Resilience Planning for Power Systems under Wildfires and Cascading Hazards. In preparation for journal submission.