Evolutionary Optimization for Designing Variational Quantum Circuits with High Model Capacity
Samuel Yen-Chi Chen
TL;DR
This work targets the design bottleneck of high-capacity quantum neural networks by introducing EvoQAS-ED, an evolutionary quantum architecture search framework that encodes circuit architectures and optimizes them with respect to an effective-dimension fitness. The ED, defined as d_gamma,n(M_Theta), derives from the Fisher information and serves as a proxy for model capacity and potential generalization. Empirical results show evolved QNNs achieving larger ED than comparable classical counterparts and exhibiting favorable Fisher information spectra, implying improved trainability and reduced barren-plateau risk. The framework is flexible and extensible, enabling adaptation to other QNN metrics and broader QML tasks on near-term quantum devices.
Abstract
Recent advancements in quantum computing (QC) and machine learning (ML) have garnered significant attention, leading to substantial efforts toward the development of quantum machine learning (QML) algorithms to address a variety of complex challenges. The design of high-performance QML models, however, requires expert-level knowledge, posing a significant barrier to the widespread adoption of QML. Key challenges include the design of data encoding mechanisms and parameterized quantum circuits, both of which critically impact the generalization capabilities of QML models. We propose a novel method that encodes quantum circuit architecture information to enable the evolution of quantum circuit designs. In this approach, the fitness function is based on the effective dimension, allowing for the optimization of quantum circuits towards higher model capacity. Through numerical simulations, we demonstrate that the proposed method is capable of discovering variational quantum circuit architectures that offer improved learning capabilities, thereby enhancing the overall performance of QML models for complex tasks.