🤖 AI Summary
Quantum neural networks (QNNs) suffer from two fundamental optimization bottlenecks: gradient vanishing and cost-function concentration—commonly termed the “barren plateau” problem. To address these, this work introduces, for the first time, the classical ensemble learning paradigm into QNN design, proposing an ensemble architecture composed of parallel single-layer parameterized quantum circuits. By favoring shallow collaborative structures over deep sequential stacking, the approach inherently mitigates gradient attenuation and optimization stagnation at the architectural level. The method integrates variational quantum algorithms, gradient sensitivity analysis, and systematic comparative experiments on classification tasks. Empirical results demonstrate that the ensemble architecture significantly enhances gradient magnitude stability, effectively suppresses barren plateaus, accelerates training convergence, and achieves superior generalization performance compared to conventional deep QNNs with equivalent parameter counts. This work establishes a novel, scalable paradigm for QNN design grounded in ensemble principles.
📝 Abstract
The rapid development of quantum computers promises transformative impacts across diverse fields of science and technology. Quantum neural networks (QNNs), as a forefront application, hold substantial potential. Despite the multitude of proposed models in the literature, persistent challenges, notably the vanishing gradient (VG) and cost function concentration (CFC) problems, impede their widespread success. In this study, we introduce a novel approach to quantum neural network construction, specifically addressing the issues of VG and CFC. Our methodology employs ensemble learning, advocating for the simultaneous deployment of multiple quantum circuits with a depth equal to $1$, a departure from the conventional use of a single quantum circuit with depth $L$. We assess the efficacy of our proposed model through a comparative analysis with a conventionally constructed QNN. The evaluation unfolds in the context of a classification problem, yielding valuable insights into the potential advantages of our innovative approach.