Quantum-Inspired Optimization Algorithms for Scalable Machine Learning in Edge Computing

Abstract

The convergence of machine learning and edge computing has led to the development of scalable solutions that bring computation closer to the data source. However, optimizing machine learning models efficiently for edge devices poses challenges due to limited resources such as power, memory, and computational capability. Quantum-inspired optimization algorithms (QIOAs) offer a promising alternative to traditional optimization techniques, providing superior performance in constrained environments. This paper explores the application of QIOAs for scalable machine learning models in edge computing. We propose a novel hybrid quantum-inspired approach, benchmark it against classical algorithms, and demonstrate its efficacy in various edge computing environments. Experimental results show improved accuracy, reduced latency, and enhanced resource utilization.