Zhanhong Jiang

Iowa State University, Johnson Controls (United States)

Papers

Total Citations

H-Index

About

Zhanhong Jiang is a researcher whose work sits at the intersection of dynamical systems, decentralized machine learning, and distributed optimization. His research focuses on developing data-driven and algorithmic frameworks to enable complex multi-agent networks—from mobile robotics to intelligent infrastructure—to learn and operate efficiently without centralized control. A key contribution is his exploration of Granger causality within dynamical systems, providing a novel method for modeling and performance monitoring in high-dimensional environments where traditional first-principle approaches fall short. In the realm of decentralized deep learning, Jiang has advanced the field by introducing momentum-accelerated consensus algorithms, which allow multiple agents to collaboratively train models on distributed datasets without relying on a central parameter server. His work on distributed optimization for control and learning further addresses the challenges of large-scale networked systems, offering scalable solutions for coordination and decision-making. With his most cited papers accumulating over a dozen citations, Jiang’s research is laying foundational groundwork for the next generation of autonomous, collaborative, and resilient multi-agent systems.