Amalendu Iyer
Papers
1
Total Citations
2
H-Index
1
About
Amalendu Iyer is a researcher at the forefront of edge computing and resource-constrained machine learning, with a focus on enabling intelligent, low-latency inference at the network’s periphery. His most cited work, "Cost-effective Machine Learning Inference Offload for Edge Computing" (2020, 2 citations), tackles a critical challenge: the prohibitive cost of transporting massive data streams from edge devices to remote cloud data centers. Iyer proposes a novel framework that intelligently offloads ML inference tasks to local edge nodes, balancing computational load and reducing bandwidth consumption while maintaining accuracy. This contribution is pivotal for real-time applications like autonomous systems and IoT, where latency and privacy are paramount. Though his citation count is modest, Iyer’s work addresses a foundational bottleneck in distributed AI, earning recognition for its practical, cost-aware design. His research bridges the gap between cloud-centric AI and the growing demand for on-device intelligence, positioning him as a promising voice in the evolution of edge-native machine learning systems.
Research Focus
Key Achievements
Top Papers
- 1Cost-effective Machine Learning Inference Offload for Edge Computing2 citations · 2020