arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.17760quant-phcs.AIcs.ETcs.LGcs.NE
收藏

利用快速权重学习编程变分量子电路

Learning to Program Variational Quantum Circuits with Fast Weights

Wells Fargo(富国银行)

Samuel Yen-Chi Chen

AI总结:

本文提出量子快速权重编程器(QFWP),通过经典慢速编程器更新变分量子电路参数以捕捉时间依赖,无需量子循环神经网络即可在时间序列预测和强化学习任务中达到或超越QLSTM模型性能。

摘要:

量子机器学习(QML)已成为解决顺序控制任务和时间序列建模的前沿框架。它已在强化学习(RL)和时间序列预测等领域展现出经验性的量子优势。一项重要进展是量子循环神经网络(QRNNs),其专门针对记忆密集型任务而设计,包括部分可观测环境和非线性时间序列预测。然而,基于QRNN的模型面临挑战,尤其是由于需要通过时间反向传播(BPTT)计算量子梯度而导致的训练时间过长。当在量子设备上执行完整模型时,这一问题会进一步加剧,主要原因是参数移位规则带来了巨大的电路评估需求。本文引入量子快速权重编程器(QFWP)作为解决时间或顺序学习挑战的方案。QFWP利用一个经典神经网络(称为“慢速编程器”)充当量子编程器,以快速修改变分量子电路(称为“快速编程器”)的参数。慢速编程器并非在每个时间步完全覆盖快速编程器,而是为量子电路参数生成参数变化或更新。这种方法使快速编程器能够纳入过去的观测或信息。值得注意的是,所提出的QFWP模型在无需使用量子循环神经网络的情况下实现了对时间依赖关系的学习。本研究中进行的数值模拟展示了所提出的QFWP模型在时间序列预测和RL任务中的有效性。该模型表现出与基于QLSTM的模型相当或超越其水平的性能。

英文摘要:

Quantum Machine Learning (QML) has surfaced as a pioneering framework addressing sequential control tasks and time-series modeling. It has demonstrated empirical quantum advantages notably within domains such as Reinforcement Learning (RL) and time-series prediction. A significant advancement lies in Quantum Recurrent Neural Networks (QRNNs), specifically tailored for memory-intensive tasks encompassing partially observable environments and non-linear time-series prediction. Nevertheless, QRNN-based models encounter challenges, notably prolonged training duration stemming from the necessity to compute quantum gradients using backpropagation-through-time (BPTT). This predicament exacerbates when executing the complete model on quantum devices, primarily due to the substantial demand for circuit evaluation arising from the parameter-shift rule. This paper introduces the Quantum Fast Weight Programmers (QFWP) as a solution to the temporal or sequential learning challenge. The QFWP leverages a classical neural network (referred to as the 'slow programmer') functioning as a quantum programmer to swiftly modify the parameters of a variational quantum circuit (termed the 'fast programmer'). Instead of completely overwriting the fast programmer at each time-step, the slow programmer generates parameter changes or updates for the quantum circuit parameters. This approach enables the fast programmer to incorporate past observations or information. Notably, the proposed QFWP model achieves learning of temporal dependencies without necessitating the use of quantum recurrent neural networks. Numerical simulations conducted in this study showcase the efficacy of the proposed QFWP model in both time-series prediction and RL tasks. The model exhibits performance levels either comparable to or surpassing those achieved by QLSTM-based models.

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。

↑