arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.09200quant-phcs.LG
收藏

一种训练宽深度经典神经网络的量子算法

A quantum algorithm for training wide and deep classical neural networks

Massachusetts Institute of Technology(麻省理工学院);Google Quantum AI(谷歌量子人工智能)

Alexander Zlokapa, Hartmut Neven, Seth Lloyd

摘要:

鉴于深度学习在经典机器学习中的成功,传统神经网络架构的量子算法可能为量子机器学习提供最有前途的环境之一。考虑到一个完全连接的前馈神经网络,我们表明,通过梯度下降服从经典可训练性的条件与有效地解决量子线性系统所需的条件一致。我们提出了一种量子算法,通过在$O(\log n)$时间内执行稀疏矩阵求逆,来近似训练一个宽而深的神经网络,以达到$n$误差。为了在梯度下降上实现端到端的指数加速,数据分布必须允许有效的状态准备和读出。我们在数值上证明了MNIST图像数据集满足这些条件;此外,量子算法与全连接网络的精度相匹配。除了经过验证的架构之外,我们还为使用池化的卷积神经网络的$O(\log n)$训练提供了经验证据。

英文摘要:

Given the success of deep learning in classical machine learning, quantum algorithms for traditional neural network architectures may provide one of the most promising settings for quantum machine learning. Considering a fully-connected feedforward neural network, we show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We propose a quantum algorithm to approximately train a wide and deep neural network up to $O(1/n)$ error for a training set of size $n$ by performing sparse matrix inversion in $O(\log n)$ time. To achieve an end-to-end exponential speedup over gradient descent, the data distribution must permit efficient state preparation and readout. We numerically demonstrate that the MNIST image dataset satisfies such conditions; moreover, the quantum algorithm matches the accuracy of the fully-connected network. Beyond the proven architecture, we provide empirical evidence for $O(\log n)$ training of a convolutional neural network with pooling.

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。

↑