arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.17630quant-phcs.AIcs.ETcs.LG
收藏

KANQAS: 用于量子架构搜索的柯尔莫哥洛夫-阿诺德网络

KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search

University of Helsinki(赫尔辛基大学);Polish Academy of Sciences(波兰科学院);Silesian University of Technology(西里西亚工业大学);Advanced Research Centre(高级研究中心);Delft University of Technology(代尔夫特理工大学);Raman Research Institute(拉曼研究所);International Institute of Information Technology, Hyderabad(海得拉巴国际信息技术学院)

Akash Kundu, Aritra Sarkar, Abhishek Sadhu

AI总结:

针对基于MLP的量子架构搜索方法可解释性差的问题,提出结合KAN的KANQAS方法,在量子态制备和量子化学任务中表现更优且参数量更少。

摘要:

量子架构搜索(Quantum Architecture Search, QAS)是面向量子优势实现量子电路优化与自动化设计的一个极具前景的方向。当前的QAS技术多采用基于多层感知器(Multi-Layer Perceptron, MLP)的深度Q网络,但这类方法因可学习参数量大、激活函数选择过程复杂,可解释性仍面临挑战。为解决上述问题,本研究将柯尔莫哥洛夫-阿诺德网络(Kolmogorov-Arnold Network, KAN)应用于QAS算法,分析其在量子态制备与量子化学任务中的效率。在量子态制备任务中,结果显示无噪声场景下,该方法的成功概率是MLP的2至5倍;在含噪环境中,KAN在逼近这些量子态时的保真度优于MLP,展现出更强的噪声鲁棒性。在处理量子化学问题时,我们将课程强化学习与KAN结构相结合,对近期提出的QAS算法进行改进,通过减少所需的两比特量子门数量与电路深度,实现了参数化量子电路更高效的设计。进一步研究表明,与MLP相比,KAN所需的可学习参数量显著更少,但每个回合的平均执行时间更长。

英文摘要:

Quantum architecture Search (QAS) is a promising direction for optimization and automated design of quantum circuits towards quantum advantage. Recent techniques in QAS emphasize Multi-Layer Perceptron (MLP)-based deep Q-networks. However, their interpretability remains challenging due to the large number of learnable parameters and the complexities involved in selecting appropriate activation functions. In this work, to overcome these challenges, we utilize the Kolmogorov-Arnold Network (KAN) in the QAS algorithm, analyzing their efficiency in the task of quantum state preparation and quantum chemistry. In quantum state preparation, our results show that in a noiseless scenario, the probability of success is 2 to 5 times higher than MLPs. In noisy environments, KAN outperforms MLPs in fidelity when approximating these states, showcasing its robustness against noise. In tackling quantum chemistry problems, we enhance the recently proposed QAS algorithm by integrating curriculum reinforcement learning with a KAN structure. This facilitates a more efficient design of parameterized quantum circuits by reducing the number of required 2-qubit gates and circuit depth. Further investigation reveals that KAN requires a significantly smaller number of learnable parameters compared to MLPs; however, the average time of executing each episode for KAN is higher.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑