Shanyang Jiang
Papers
1
Total Citations
1
H-Index
1
About
Shanyang Jiang is a rising researcher in the fields of distributed optimization, online learning, and multi-agent systems. Their work addresses a critical bottleneck in modern AI: how to enable large-scale, collaborative learning under severe communication constraints. Jiang’s most-cited paper, "Communication-Efficient Regret-Optimal Distributed Online Convex Optimization" (2024), tackles the fundamental tension between learning performance and communication overhead in networks like robot swarms and IoT devices. By achieving regret-optimality while dramatically reducing the number of messages exchanged, this work provides a theoretical foundation for practical, scalable coordination. Though early in their career, Jiang’s contributions are already shaping how researchers design algorithms for bandwidth-limited, real-time environments. Their focus on balancing theoretical guarantees with real-world constraints positions them as a key voice in the next generation of distributed AI—making their work essential reading for anyone interested in deploying learning systems where every bit counts.
Research Focus
Key Achievements
Top Papers
- 1