Quantum Architecture Search with Meta‐Learning. Issue 8 (17th June 2022)

• Record Type: Journal Article
• Authors: He, Zhimin; Chen, Chuangtao; Li, Lvzhou; Zheng, Shenggen; Situ, Haozhen
• Is Part Of: Advanced quantum technologies. Volume 5:Issue 8(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-06-17
• Subjects: meta‐learning -- quantum architecture search -- variational quantum algorithms; Quantum theory -- Periodicals; Quantum computing -- Periodicals; Quantum chemistry -- Periodicals; Quantum electronics -- Periodicals; 537.5
• DOI: 10.1002/qute.202100134
• Languages: English
• ISSNs: 2511-9044

Abstract

Abstract: Variational quantum algorithms (VQAs) have been successfully applied to quantum approximate optimization algorithms, variational quantum compiling and quantum machine learning models. The performances of VQAs largely depend on the architecture of parameterized quantum circuits (PQCs). Quantum architecture search (QAS) aims to automate the design of PQCs in different VQAs with classical optimization algorithms. However, current QAS algorithms do not use prior experiences and search the quantum architecture from scratch for each new task, which is inefficient and time consuming. In this paper, a meta quantum architecture search (MetaQAS) algorithm is proposed, which learns good initialization heuristics of the architecture (i.e., meta‐architecture), along with the meta‐parameters of quantum gates from a number of training tasks such that they can adapt to new tasks with fewer gradient updates, which leads to fast learning on new tasks. The proposed MetaQAS can be used with arbitrary gradient‐based QAS algorithms. Simulation results on variational quantum compiling (VQC) and quantum approximate optimization algorithm (QAOA) show that the architectures optimized by MetaQAS converge faster than a state‐of‐the‐art gradient‐based QAS algorithm, namely DQAS. MetaQAS also achieves a better solution than DQAS after fine‐tuning of gate parameters. Abstract : A meta quantum architecture search (MetaQAS) algorithm is proposed to learn good initialization heuristics of the architecture (i.e., meta‐architecture), along with the meta‐parameters of quantum gates from a number of training tasks, which enables better learning on new tasks. Numerical results show the effectiveness of MetaQAS on variational quantum compiling and quantum approximate optimization algorithms.