KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search
This work addresses interpretability and performance issues in quantum circuit design for researchers in quantum computing, though it is incremental as it builds on existing QAS methods by integrating KANs.
The paper tackles the challenge of interpretability and efficiency in Quantum Architecture Search (QAS) by using Kolmogorov-Arnold Networks (KANs) instead of Multi-Layer Perceptrons (MLPs), resulting in a 2 to 5 times higher probability of success in quantum state preparation and improved fidelity in noisy environments, along with reduced circuit depth and gate count in quantum chemistry tasks.
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.