arXiv:2605.27410v2 Announce Type: replace-cross 
Abstract: Variational Quantum Algorithms (VQAs) are a leading approach to exploiting near-term quantum hardware, leveraging parameterized quantum circuits and classical optimization to achieve advantage. Despite their promise, the practical deployment of VQAs is challenged by the difficulty of designing quantum circuit architectures that balance expressivity, trainability, and hardware constraints. Existing evolutionary-based quantum neural architecture search methods address these challenges but suffer from high computational costs due to repeated training of candidate circuits. In this work, we identify a setting in which the Gram matrix of the Quantum Neural Tangent Kernel converges. Building on this observation, we design a zero-shot surrogate model to estimate candidate performance without full training, significantly accelerating the architecture search process. Using this surrogate, we propose MZeQAS, a Monte Carlo Tree Search (MCTS)-based Zero-Shot Quantum Neural Architecture Search framework for VQAs. By integrating proxy-based performance estimation with MCTS exploration, MZeQAS efficiently discovers high-performing architectures. Experimental results demonstrate that MZeQAS outperforms existing approaches in terms of both search efficiency and solution quality, providing a scalable and effective framework for advancing VQA deployment on noisy intermediate-scale quantum devices.

تقدم دراسة حديثة نموذج MZeQAS، وهو نموذج بديل بدون تدريب مصمم لتحسين كفاءة البحث عن بنى الشبكات العصبية الكمومية من خلال تقدير أداء المرشحين دون الحاجة إلى تدريب كامل للدارات الكمومية. تتناول هذه الابتكار التحديات التي تواجه الخوارزميات الكمومية المتغيرة (VQAs) في تحقيق التوازن بين التعبيرية، وقابلية التدريب، وقيود الأجهزة.

Un estudio reciente presenta MZeQAS, un modelo de sustitución sin entrenamiento diseñado para mejorar la eficiencia de la búsqueda de arquitecturas neuronales cuánticas al estimar el rendimiento de los candidatos sin necesidad de un entrenamiento completo de los circuitos cuánticos. Esta innovación aborda los desafíos que enfrentan los Algoritmos Cuánticos Variacionales (VQAs) para equilibrar expresividad, entrenabilidad y restricciones de hardware.

Une étude récente présente MZeQAS, un modèle de substitution sans entraînement conçu pour améliorer l'efficacité de la recherche d'architecture neuronale quantique en estimant la performance des candidats sans nécessiter un entraînement complet des circuits quantiques. Cette innovation répond aux défis rencontrés par les algorithmes quantiques variationnels (VQAs) pour équilibrer expressivité, entraînabilité et contraintes matérielles.

A recent study introduces MZeQAS, a zero-shot surrogate model designed to enhance the efficiency of Quantum Neural Architecture Search by estimating candidate performance without the need for full training of quantum circuits. This innovation addresses the challenges faced by Variational Quantum Algorithms (VQAs) in balancing expressivity, trainability, and hardware constraints.