Hamid R. Rabiee

Sharif University of Technology

Papers

1

Total Citations

31

H-Index

1

About

Hamid R. Rabiee is a leading figure in distributed machine learning, signal processing, and network science, whose work bridges theoretical foundations with real-world data challenges. His research centers on developing efficient, scalable algorithms for learning over geographically distributed networks, where communication constraints and data privacy are paramount. A hallmark contribution is his work on log-scale quantization in distributed first-order methods, which addresses the critical bottleneck of bandwidth-limited communication in decentralized learning systems. By enabling gradient-based learning from distributed data with reduced precision, his methods allow multiple nodes—each holding private local cost functions—to collaboratively minimize a global objective without sacrificing convergence guarantees. This work, published in 2025 and garnering 31 citations in a short span, exemplifies his impact on practical large-scale learning. Beyond this, Rabiee has made influential advances in social network analysis, multimedia systems, and cyber-physical security, with his papers collectively amassing thousands of citations. As a professor at Sharif University of Technology and director of the Digital Signal Processing Research Lab, he has shaped a generation of researchers, earning recognition for both his theoretical rigor and his commitment to deploying AI solutions in resource-constrained environments.

Research Focus

Key Achievements

1
H-Index
1
Papers
31
Total Citations
31
Avg Citations/Paper
🏆 Most Cited Paper
Notice of Removal: Log-Scale Quantization in Distributed First-Order Methods: Gradient-Based Learning From Distributed Data
31 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: Sharif University of Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 15 days ago