Zhongxiang Dai
Papers
1
Total Citations
3
H-Index
1
About
Zhongxiang Dai is a researcher whose work lies at the intersection of machine learning, Bayesian optimization, and risk-aware decision-making. His key contributions focus on developing principled frameworks for optimizing black-box functions under uncertainty, with a particular emphasis on financial and engineering applications where risk management is critical. In his highly cited work, "Value-at-Risk Optimization with Gaussian Processes" (2021), Dai introduced the V-UCB algorithm—a novel method for maximizing Value-at-Risk (VaR) of an unknown objective function. This work stands out for providing the first no-regret guarantee in VaR optimization, a significant theoretical advancement that bridges Gaussian process optimization with risk-sensitive criteria. While his citation count is still growing, the impact of this research is evident in its foundational role for subsequent work on risk-averse Bayesian optimization. Dai’s research is particularly valuable for students and practitioners seeking to apply machine learning in domains like portfolio optimization, engineering design, and autonomous systems, where balancing exploration with worst-case risk is essential. His work exemplifies how rigorous theoretical guarantees can be married with practical risk metrics.
Research Focus
Key Achievements
Top Papers
- 1Value-at-Risk Optimization with Gaussian Processes3 citations · 2021