Safe Zeroth-Order Optimization Using Quadratic Local Approximations
Automatica, vol. 174, pp. 112141, 2025
Baiwei Guo 郭佰威
Assistant Professor
School of Science and Engineering (SSE)
The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)
The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)
I am an Assistant Professor at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen). Prior to joining CUHK-Shenzhen, I worked in industry for over two years, with hands-on experience in building hardware data models and deploying design-automation solutions in real-world settings.
I received my Ph.D. in Electrical Engineering from EPF Lausanne (EPFL), Switzerland, co-advised by Prof. Giancarlo Ferrari-Trecate and Prof. Maryam Kamgarpour. Prior to that, I obtained my M.Sc. in Electrical Engineering and Information Technology from ETH Zürich.
My research sits at the intersection of Control Theory, Mathematical Optimization, and Machine Learning, with an emphasis on developing safe, sample-efficient algorithms for real-world cyber-physical and automated engineering systems.
We are seeking highly motivated students and researchers with strong mathematical foundations and programming capabilities to join our group at CUHK-Shenzhen. Candidates from Electrical Engineering, Computer Science, Automation, Applied Mathematics, and related fields are warmly welcome.
- Ph.D. Students & Postdocs: Fully funded positions are available with competitive financial support.
- Research Assistants (RA) & Visiting Students: Positions open year-round for candidates aiming to publish top-tier papers or prepare for top graduate programs.
- Undergraduate Interns: CUHK-Shenzhen and external undergraduate students interested in theory + hands-on implementation are encouraged to reach out.
How to Apply: If you are interested, please send an email to guobaiwei@cuhk.edu.cn with the subject format [Application - Position] Your Name - University. Please attach your CV, transcripts, and any representative publications/code links.
Research Directions
Safe & Sample-Efficient BO
Safe and Efficient AI-driven Black-Box Optimization
Optimization frameworks for complex systems without analytical objective functions or constraint formulations. We focus on guaranteeing strict constraint satisfaction during exploration (safety) while dramatically improving sample efficiency. Recent efforts integrate Bayesian Optimization (BO) with Reinforcement Learning and Generative Foundation Models (e.g., Diffusion Models for BO) to enable rapid, reliable deployment on real-world systems and lifelong learning tasks.
Data-Driven Robust Control
Data-Driven Robust Control & RL-MPC
Direct data-driven receding-horizon control methodologies without explicit system identification bottlenecks. By conducting perturbation analysis on behavioral system models (e.g., Willems' fundamental lemma) and synthesizing predictive control with policy optimization, we develop safe controllers that maintain robustness against system uncertainties, non-Gaussian disturbances, and non-stationary dynamic environments.
Hardware-Algorithm Co-Design
Expertise-Driven Hardware Design Automation & Co-Synthesis
Developing automated hardware design frameworks based on multi-modal black-box optimization. We incorporate domain-specific human expertise and multi-modal models to prune suboptimal design subspaces. Furthermore, we explore the co-synthesis of hardware architectures and control algorithms, jointly optimizing physical parameters and feedback policies using proxy models and warm-start acceleration.
Selected Publications
* indicates equal contribution. Full list available on Google Scholar.
Automatica 2025
IEEE TAC 2023
Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data
IEEE Transactions on Automatic Control (TAC), vol. 68, no. 5, pp. 2699–2714, May 2023
ECC Award Paper
Safe Zeroth-Order Convex Optimization with Unknown Constraints
European Control Conference (ECC), 2023
🏆 Best Student Paper Award (1/300+)
IEEE TAC 2021
Actuator Placement Under Structural Controllability Using Forward and Reverse Greedy Algorithms
IEEE Transactions on Automatic Control (TAC), vol. 66, no. 12, pp. 5845–5860, Dec. 2021
EJOR 2021
A Comment on Guarantees of a Greedy Algorithm
European Journal of Operational Research (EJOR), vol. 290, no. 1, 2021
arXiv 2023
Data-Driven Robust Control Based on Perturbation Analysis of the Behavioral Model
arXiv:2308.14178, 2023
Honors & Awards
- Best Student Paper Award, European Control Conference (ECC) (1/300+), 2023
- Nomination for Thesis Distinction, EPF Lausanne (EPFL), 2023
- Scholarship for International Students, ETH Zürich, 2017
- Outstanding Graduate Student, Harbin Institute of Technology, 2016
- Outstanding Undergraduate in Heilongjiang Province (Top 5 out of 284), 2016
- Meritorious Winner, Mathematical Contest in Modeling (MCM, Top 5%), 2015
- First Prize, China Undergraduate Mathematical Competitions (10th in 300+), 2014