Training Variational Quantum Circuits Using Particle Swarm Optimization

2025-09-19

AI Summary

To address the barren-plateau problem hindering gradient-based optimization in variational quantum circuit (VQC) training, this paper proposes the first end-to-end, full-structure training framework based on particle swarm optimization (PSO). The method jointly optimizes quantum gate types (Rx/Ry/Rz/CNOT), target qubits, and rotation parameters—bypassing gradient computation entirely and thereby mitigating convergence difficulties arising from flat parameter landscapes. Evaluated on MedMNIST for multi-modal biomedical image classification, PSO-VQC achieves accuracy comparable to or exceeding that of gradient-based methods while using significantly fewer quantum gates. Key contributions are: (1) the first application of PSO to simultaneous VQC architecture search and parameter optimization; (2) a paradigm shift away from gradient dependence, enhancing training robustness and structural search efficiency; and (3) empirical validation of gradient-free optimization as a practical and effective approach in quantum machine learning.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

In this work, the Particle Swarm Optimization (PSO) algorithm has been used to train various Variational Quantum Circuits (VQCs). This approach is motivated by the fact that commonly used gradient-based optimization methods can suffer from the barren plateaus problem. PSO is a stochastic optimization technique inspired by the collective behavior of a swarm of birds. The dimension of the swarm, the number of iterations of the algorithm, and the number of trainable parameters can be set. In this study, PSO has been used to train the entire structure of VQCs, allowing it to select which quantum gates to apply, the target qubits, and the rotation angle, in case a rotation is chosen. The algorithm is restricted to choosing from four types of gates: Rx, Ry, Rz, and CNOT. The proposed optimization approach has been tested on various datasets of the MedMNIST, which is a collection of biomedical image datasets designed for image classification tasks. Performance has been compared with the results achieved by classical stochastic gradient descent applied to a predefined VQC. The results show that the PSO can achieve comparable or even better classification accuracy across multiple datasets, despite the PSO using a lower number of quantum gates than the VQC used with gradient descent optimization.

Problem

• Optimizing variational quantum circuits with particle swarm optimization
• Addressing barren plateaus in quantum circuit training
• Improving biomedical image classification accuracy with quantum algorithms

Innovation

• Particle Swarm Optimization trains Variational Quantum Circuits
• Overcomes barren plateaus with swarm-based stochastic optimization
• Selects quantum gates and parameters without gradient methods