arXiv:2504.02251v2 Announce Type: replace 
Abstract: The Lipschitz bandit is a key variant of stochastic bandit problems where the expected reward function satisfies a Lipschitz condition with respect to an arm metric space. With its wide-ranging practical applications, various Lipschitz bandit algorithms have been developed, achieving the cumulative regret lower bound of order $\tilde O(T^{(d_z+1)/(d_z+2)})$ over time horizon $T$. Motivated by recent advancements in quantum computing and the demonstrated success of quantum Monte Carlo in simpler bandit settings, we introduce the first quantum Lipschitz bandit algorithms to address the challenges of continuous action spaces and non-linear reward functions. Specifically, we first leverage the elimination-based framework to propose an efficient quantum Lipschitz bandit algorithm named Q-LAE. Next, we present novel modifications to the classical Zooming algorithm, which results in a simple quantum Lipschitz bandit method, Q-Zooming. Both algorithms exploit the computational power of quantum methods to achieve an improved regret bound of $\tilde O(T^{d_z/(d_z+1)})$. Comprehensive experiments further validate our improved theoretical findings, demonstrating superior empirical performance compared to existing Lipschitz bandit methods.

يمثل إدخال خوارزميات bandit Lipschitz الكم تقدمًا كبيرًا في معالجة التحديات المرتبطة بمساحات العمل المستمرة ودوال المكافأة غير الخطية في مشاكل bandit العشوائية. تستفيد الخوارزميات المقترحة، Q-LAE و Q-Zooming، من تقنيات الحوسبة الكمومية لتعزيز الكفاءة والأداء في هذه السيناريوهات المعقدة.

La introducción de algoritmos de bandido Lipschitz cuánticos marca un avance significativo en la resolución de desafíos asociados con espacios de acción continuos y funciones de recompensa no lineales en problemas de bandidos estocásticos. Los algoritmos propuestos, Q-LAE y Q-Zooming, aprovechan las técnicas de computación cuántica para mejorar la eficiencia y el rendimiento en estos escenarios complejos.

L'introduction des algorithmes de bandits Lipschitz quantiques représente une avancée significative pour relever les défis liés aux espaces d'action continus et aux fonctions de récompense non linéaires dans les problèmes de bandits stochastiques. Les algorithmes proposés, Q-LAE et Q-Zooming, exploitent les techniques de calcul quantique pour améliorer l'efficacité et la performance dans ces scénarios complexes.

The introduction of quantum Lipschitz bandit algorithms marks a significant advancement in addressing challenges associated with continuous action spaces and non-linear reward functions in stochastic bandit problems. The proposed algorithms, Q-LAE and Q-Zooming, leverage quantum computing techniques to enhance efficiency and performance in these complex scenarios.

Quantum Lipschitz Bandits

arXiv:2512.07808v1 Announce Type: cross 
Abstract: Qubit readout is a critical operation in quantum computing systems, which maps the analog response of qubits into discrete classical states. Deep neural networks (DNNs) have recently emerged as a promising solution to improve readout accuracy . Prior hardware implementations of DNN-based readout are resource-intensive and suffer from high inference latency, limiting their practical use in low-latency decoding and quantum error correction (QEC) loops. This paper proposes LUNA, a fast and efficient superconducting qubit readout accelerator that combines low-cost integrator-based preprocessing with Look-Up Table (LUT) based neural networks for classification. The architecture uses simple integrators for dimensionality reduction with minimal hardware overhead, and employs LogicNets (DNNs synthesized into LUT logic) to drastically reduce resource usage while enabling ultra-low-latency inference. We integrate this with a differential evolution based exploration and optimization framework to identify high-quality design points. Our results show up to a 10.95x reduction in area and 30% lower latency with little to no loss in fidelity compared to the state-of-the-art. LUNA enables scalable, low-footprint, and high-speed qubit readout, supporting the development of larger and more reliable quantum computing systems.

تم اقتراح بنية جديدة تُدعى LUNA لتحسين قراءة الكيوبتات في الحوسبة الكمومية، باستخدام مزيج من المعالجة المسبقة القائمة على المُتكاملات منخفضة التكلفة والشبكات العصبية القائمة على جداول البحث (LUT). تهدف هذه الطريقة إلى تحسين دقة وسرعة قراءة الكيوبتات، وهو أمر أساسي لتصحيح الأخطاء الكمومية وعمليات فك التشفير ذات الكمون المنخفض.

Se ha propuesto una nueva arquitectura llamada LUNA para mejorar la lectura de qubits en la computación cuántica, utilizando una combinación de preprocesamiento basado en integradores de bajo costo y redes neuronales basadas en tablas de búsqueda (LUT). Este enfoque busca mejorar la precisión y velocidad de la lectura de qubits, que es esencial para la corrección de errores cuánticos y los procesos de decodificación de baja latencia.

Une nouvelle architecture nommée LUNA a été proposée pour améliorer la lecture des qubits dans l'informatique quantique, utilisant une combinaison de prétraitement basé sur des intégrateurs à faible coût et de réseaux neuronaux basés sur des tables de correspondance (LUT). Cette approche vise à améliorer la précision et la rapidité de la lecture des qubits, essentielle pour la correction d'erreurs quantiques et les processus de décodage à faible latence.

A new architecture named LUNA has been proposed to enhance qubit readout in quantum computing, utilizing a combination of low-cost integrator-based preprocessing and Look-Up Table (LUT) based neural networks. This approach aims to improve the accuracy and speed of qubit readout, which is essential for quantum error correction and low-latency decoding processes.

Quantum Lipschitz Bandits

Was this article worth reading? Share it

LucidQuery AI

Aqaba.ai

Hummingbot