arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.11463quant-phcs.AIstat.ML
收藏

量子计算机上的贝叶斯深度学习

Bayesian Deep Learning on a Quantum Computer

ETH Zurich(苏黎世联邦理工学院);Singapore University of Technology and Design(新加坡科技设计大学);National University of Singapore(新加坡国立大学);ICFO-Institut de Ciencies Fotoniques, The Barcelona Institute of Science and Technology(巴塞罗那科学技术学院光子科学研究所);University of Toronto(多伦多大学);Creative Destruction Lab(创造性破坏实验室);Vector Institute for Artificial Intelligence(向量人工智能研究所);Perimeter Institute for Theoretical Physics(圆周理论物理研究所)

Zhikuan Zhao, Alejandro Pozas-Kerstjens, Patrick Rebentrost, Peter Wittek

摘要:

机器学习中的贝叶斯方法,如高斯过程,与其他技术相比具有很大的优势。特别是,它们提供了与预测相关的不确定性的估计。将贝叶斯方法扩展到深层架构仍然是一个重大挑战。最近的结果将深度前向神经网络与高斯过程连接起来,允许在没有反向传播的情况下进行训练。这种联系使我们能够利用为高斯过程设计的量子算法,并在量子计算机上开发贝叶斯深度学习的新算法。高斯过程中的核矩阵的属性确保了协议的核心组件量子矩阵求逆的有效执行,提供了至少多项式的加速比。此外,我们展示了该算法在当代量子计算机上的执行,并分析了其相对于现实噪声模型的鲁棒性。

英文摘要:

Bayesian methods in machine learning, such as Gaussian processes, have great advantages com-pared to other techniques. In particular, they provide estimates of the uncertainty associated with a prediction. Extending the Bayesian approach to deep architectures has remained a major challenge. Recent results connected deep feedforward neural networks with Gaussian processes, allowing training without backpropagation. This connection enables us to leverage a quantum algorithm designed for Gaussian processes and develop a new algorithm for Bayesian deep learning on quantum computers. The properties of the kernel matrix in the Gaussian process ensure the efficient execution of the core component of the protocol, quantum matrix inversion, providing an at least polynomial speedup over classical algorithms. Furthermore, we demonstrate the execution of the algorithm on contemporary quantum computers and analyze its robustness with respect to realistic noise 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。

↑