Quantum architecture search~(QAS) is a promising direction for optimization and automated design of quantum circuits towards quantum advantage. Recent techniques in QAS focus on machine learning-based approaches from reinforcement learning, like deep Q-network. While multi-layer perceptron-based deep Q-networks have been applied for QAS, their interpretability remains challenging due to the high number of parameters. In this work, we evaluate the practicality of KANs in quantum architecture search problems, analyzing their efficiency in terms of the probability of success, frequency of optimal solutions and their dependencies on various degrees of freedom of the network. In a noiseless scenario, the probability of success and the number of optimal quantum circuit configurations to generate the multi-qubit maximally entangled states are significantly higher than MLPs. Moreover in noisy scenarios, KAN can achieve a better fidelity in approximating maximally entangled state than MLPs, where the performance of the MLP significantly depends on the choice of activation function. Further investigation reveals that KAN requires a very small number of learnable parameters compared to MLPs, however, the average time of executing each episode for KAN is much higher.

翻译：量子架构搜索（QAS）是优化和自动设计量子电路以实现量子优势的一个有前景的方向。QAS中的最新技术侧重于基于机器学习的方法，例如深度Q网络等强化学习技术。虽然基于多层感知机的深度Q网络已应用于QAS，但由于参数数量庞大，其可解释性仍然面临挑战。在本工作中，我们评估了Kolmogorov-Arnold网络（KAN）在量子架构搜索问题中的实用性，分析了其在成功概率、最优解频率方面的效率，以及这些效率与网络各种自由度之间的依赖关系。在无噪声场景下，KAN生成多量子比特最大纠缠态的成功概率和最优量子电路配置数量均显著高于多层感知机。此外，在噪声场景中，KAN在近似最大纠缠态时能达到比多层感知机更好的保真度，而多层感知机的性能则显著依赖于激活函数的选择。进一步研究表明，与多层感知机相比，KAN所需的可学习参数数量极少，但KAN执行每个训练回合的平均时间要长得多。