Scholar
Yang Zheng
Google Scholar ID: hm5XrmoAAAAJ
Assistant Professor, UC San Diego
Citations & Impact
Citations
6,273
H-index
38
i10-index
67
Publications
20
Co-authors
68
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Publications: 'An Overview and Comparison of Spectral Bundle Methods for Primal and Dual Semidefinite Programs' accepted for publication in Computational Optimization and Applications.
- - Awards: July 2025, received the Donald P. Eckman Award from the American Automatic Control Council, recognizing fundamental contributions to convex and non-convex optimization in optimal and distributed control, scalable computational techniques, and transformative applications in traffic systems.
- - Preprints: 'A Proximal Descent Method for Minimizing Weakly Convex Optimization', 'Regularization in Data-driven Predictive Control: A Convex Relaxation Perspective', 'Logarithmic Regret and Polynomial Scaling in Online Multi-step-ahead Prediction', 'Model-free Online Learning for the Kalman Filter: Forgetting Factor and Logarithmic Regret', 'Dictionary-free Koopman Predictive Control for Autonomous Vehicles in Mixed Traffic', 'Semidefinite Programming Duality in Infinite-Horizon Linear Quadratic Differential Games'.
Research Experience
- - March 2019 to August 2020, Postdoctoral Scholar at SEAS and CGBC, Harvard University, working with Prof. Na Li and Prof. Ali Malkawi.
- - 2021, Research Associate in the Verification of Autonomous Systems group at Imperial College London.
Education
- - Ph.D.: February 2019, University of Oxford, Control, supervised by Prof. Antonis Papachristodoulou.
- - M.E.: 2015, Tsinghua University, Department of Automotive Engineering, Beijing, China.
- - B.S.: 2013, Tsinghua University, Department of Automotive Engineering, Beijing, China.
Background
- - Research Interests: Learning, optimization, and control of network systems, with applications to autonomous vehicles and traffic systems.
- - Professional Fields: Convex and non-convex optimization for control, principled data-driven and learning-based control, structures and algorithms for scalable conic optimization, mixed traffic control, and certifiable robustness of machine learning (e.g., deep neural networks).
Miscellany
- - Prospective Students: Actively seeking highly motivated students with a strong background in mathematics, theory, and computation to join his research group. Applicants can contact via email and include their CV, transcripts, and a brief overview of their interest in joining the group.
