KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search

TL;DR

This paper introduces KANQAS, a quantum architecture search method using Kolmogorov-Arnold Networks, which improves quantum state preparation success rates and circuit efficiency over traditional MLP-based approaches, especially in noisy environments.

Contribution

The paper proposes integrating Kolmogorov-Arnold Networks into quantum architecture search, enhancing interpretability, robustness, and efficiency in quantum circuit design compared to existing MLP-based methods.

Findings

KAN outperforms MLPs in noiseless quantum state preparation

KAN achieves higher fidelity in noisy environments

KAN reduces the number of 2-qubit gates and circuit depth

Abstract

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.