arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06258quant-ph
收藏

量子神经网络的可训练性

Toward Trainability of Quantum Neural Networks

Kaining Zhang, Min-Hsiu Hsieh, Liu Liu, Dacheng Tao

摘要:

量子神经网络(QNN)是近年来提出的经典神经网络的推广,以实现量子加速。尽管有可能超越经典模型,但训练QNN存在严重的瓶颈;即,具有随机结构的QNN由于与输入量子比特数成指数的消失梯度而具有较差的可训练性。消失梯度会严重影响大规模QNN的应用。在这项工作中,我们提供了一个可行的解决方案与理论保证。具体来说,我们证明了树张量和步进控制架构的QNN具有最多随量子比特数多项式消失的梯度。我们数值演示了QNN与树张量和步骤控制结构的二元分类的应用。仿真结果表明,更快的收敛速度和更好的精度相比,随机结构的QNN。

英文摘要:

Quantum Neural Networks (QNNs) have been recently proposed as generalizations of classical neural networks to achieve the quantum speed-up. Despite the potential to outperform classical models, serious bottlenecks exist for training QNNs; namely, QNNs with random structures have poor trainability due to the vanishing gradient with rate exponential to the input qubit number. The vanishing gradient could seriously influence the applications of large-size QNNs. In this work, we provide a viable solution with theoretical guarantees. Specifically, we prove that QNNs with tree tensor and step controlled architectures have gradients that vanish at most polynomially with the qubit number. We numerically demonstrate QNNs with tree tensor and step controlled structures for the application of binary classification. Simulations show faster convergent rates and better accuracy compared to QNNs with random structures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑