Halfway Escape Optimization: A Quantum-Inspired Solution for General Optimization Problems

TL;DR

HEO introduces a quantum-inspired optimization framework featuring energy-driven dynamics, vibration, center clipping, and random skip to balance exploration and exploitation. Evaluations on 14 benchmark functions at dimension $D=30$ plus classical engineering problems (Pressure Vessel Design, Tubular Column Design) and real-time tasks (logistic regression parameter tuning, rice classification) demonstrate fast convergence and competitive accuracy relative to PSO, GA, AFSA, GWO, and QPSO. Overall, HEO achieves strong performance across unimodal and multimodal landscapes with acceptable runtimes, while identifying certain constraint-specific weaknesses. The work suggests substantial practical impact for general optimization and points to future enhancements including multi-objective capabilities and dynamic environment adaptation.

Abstract

This paper first proposes the Halfway Escape Optimization (HEO) algorithm, a quantum-inspired metaheuristic designed to address general optimization problems. The HEO mimics the effects between quantum such as tunneling, entanglement. After the introduction to the HEO mechansims, the study presents a comprehensive evaluation of HEO's performance against extensively-used optimization algorithms, including Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Artificial Fish Swarm Algorithm (AFSA), Grey Wolf Optimizer (GWO), and Quantum behaved Particle Swarm Optimization (QPSO). The primary analysis encompasses 14 benchmark functions with dimension 30, demonstrating HEO's effectiveness and adaptability in navigating general optimization problems. The test of HEO in Pressure Vessel Design and Tubular Column Design also infers its feasibility and potential in real-time applications. Further validation of HEO in Osmancik-97 and Cammeo Rice Classification achieves a higher accuracy record.

Figures (16)

• Figure 1: Simplified Flowchart of One Iteration in HEO
• Figure 2: Position Update in HEO
• Figure 3: Scaling Function
• Figure 4: Center Clipping in Ackley Function
• Figure 5: The cost variation in $F_{1}$ and $F_{2}$