I am a Postdoctoral Researcher in the Department of Chemical and Biological Engineering at the University of Wisconsin–Madison, working with Prof. Styliani Avraamidou and Prof. Victor M. Zavala. I received my Ph.D. in Chemical Engineering from the University of British Columbia in 2026 under the supervision of Prof. Yankai Cao, and my Bachelor’s and Master’s degrees from the College of Control Science and Engineering at Zhejiang University in 2018 and 2021 under the supervision of Prof. Dong Ni.
My research develops optimization algorithms and interpretable machine learning for decision-making in process, energy, and manufacturing systems. My current work focuses on decision-focused and surrogate-based optimization: designing surrogates specifically for optimization problems such as single-level, bilevel, multi-level, two-stage stochastic, and multi-stage programs. During my Ph.D., I built global optimization algorithms that train interpretable models (clustering and optimal decision trees) on up to one billion samples, and used oblique decision trees to learn model predictive control laws that run over 1,000× faster than online MPC.
Research Interests
- Decision-focused and surrogate-based optimization.
- Global optimization algorithms for large-scale interpretable machine learning.
- Learning-based control with interpretable models.
- Data-driven modeling, monitoring, and control of manufacturing, energy, and process systems.
News
- Started as a Postdoctoral Researcher at UW–Madison, working with Prof. Styliani Avraamidou and Prof. Victor M. Zavala.
- Our paper “A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees” is accepted by Transactions on Machine Learning Research with a J2C Certification.
- Our paper “A Moving-Horizon Differential Evolution Algorithm for Training Deep Classification Trees on Large Datasets” is published in Expert Systems with Applications. The code is released as the open-source Julia package MHDETrees.jl.
- Presented two papers at the 23rd IFAC World Congress, on interpretable quadcopter control with decision trees and interpretable reinforcement learning for multi-loop adaptive PID control.
- Completed my Ph.D. in Chemical Engineering at the University of British Columbia. Many thanks to my advisor Prof. Yankai Cao.
Show all news (13)Show less
- Presented our paper “Exact Learning of Linear Model Predictive Control Laws using Oblique Decision Trees with Linear Predictions” at the 64th IEEE Conference on Decision and Control.
- Honored to be a Finalist for the AIChE CAST Director’s Student Presentation Award, presenting my work on interpretable machine learning for process control.
- Our paper “Differentiable Decision Tree via ‘ReLU+Argmin’ Reformulation” is accepted by NeurIPS 2025 as a Spotlight.
- Honored to receive the Wall Research Award.
- Our paper “A Global Optimization Algorithm for K-Center Clustering of One Billion Samples” is accepted by Management Science.
- Our paper “Hierarchical model predictive control for energy consumption regulation of industrial-scale circulation counter-flow paddy drying process” is accepted by Energy.
- Our paper “Deep Learning-Based Approximation of Model Predictive Control Laws Using Mixture Networks” is accepted by IEEE Transactions on Automation Science and Engineering.
- Two papers on global optimization of large-scale K-Medoids clustering and decision trees are accepted by NeurIPS 2022.
Contact
- rjy12307@outlook.com
- Department of Chemical & Biological Engineering
University of Wisconsin–Madison
1415 Engineering Drive, Madison, WI 53706, USA