Zebang Shen
Papers
1
Total Citations
3
H-Index
1
About
Zebang Shen is a rising researcher in machine learning and optimization, whose work focuses on developing algorithms that are both efficient and safe for real-world applications. His primary research areas include safe reinforcement learning, constrained optimization, and non-convex optimization under uncertainty. Shen’s most notable contribution is his pioneering work on "Safe Learning under Uncertain Objectives and Constraints" (2020), which addresses the critical challenge of optimizing non-convex problems when safety constraints are unknown—a common scenario in robotics, manufacturing, and medical procedures. This paper, with 3 citations, lays foundational groundwork for algorithms that can learn optimal policies while respecting unmodeled safety limits, bridging the gap between theoretical optimization and practical deployment. Beyond this, Shen has made significant strides in understanding the convergence properties of stochastic gradient methods and developing robust optimization frameworks. His research is particularly impactful for students and engineers working on autonomous systems, where ensuring safety during learning is paramount. As a young researcher, Shen’s work signals a promising trajectory toward more reliable and trustworthy AI systems.
Research Focus
Key Achievements
Top Papers
- 1Safe Learning under Uncertain Objectives and Constraints3 citations · 2020