arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.11537quant-phcond-mat.str-elcs.LG
收藏

用张量网络实现量子机器学习

Towards Quantum Machine Learning with Tensor Networks

University of California Berkeley(加州大学伯克利分校);Center for Computational Quantum Physics, Flatiron Institute(计算量子物理中心,弗莱托恩研究所)

William Huggins, Piyush Patel, K. Birgitta Whaley, E. Miles Stoudenmire

摘要:

机器学习是量子计算的一个很有前途的应用,但挑战仍然存在,因为短期设备的物理量子比特数量有限,错误率很高。受张量网络在经典背景下用于机器学习的有用性的启发,我们提出了量子计算方法来进行判别学习和生成学习,其电路基于树和矩阵乘积状态张量网络,可能对近期设备有好处。其结果是一个统一的框架,其中经典和量子计算可以受益于相同的理论和算法发展,并且可以经典地训练相同的模型,然后将其转移到量子设置以进行额外的优化。张量网络电路还可以提供量子位高效方案,其中根据架构,所需的物理量子位的数量仅与输入或输出数据大小成比例,或独立于输入或输出数据大小。我们通过数值实验证明了我们的建议,训练一个判别模型,使用可以在量子硬件上进行的优化过程来执行手写识别,并测试训练模型的抗噪能力。

英文摘要:

Machine learning is a promising application of quantum computing, but challenges remain as near-term devices will have a limited number of physical qubits and high error rates. Motivated by the usefulness of tensor networks for machine learning in the classical context, we propose quantum computing approaches to both discriminative and generative learning, with circuits based on tree and matrix product state tensor networks that could have benefits for near-term devices. The result is a unified framework where classical and quantum computing can benefit from the same theoretical and algorithmic developments, and the same model can be trained classically then transferred to the quantum setting for additional optimization. Tensor network circuits can also provide qubit-efficient schemes where, depending on the architecture, the number of physical qubits required scales only logarithmically with, or independently of the input or output data sizes. We demonstrate our proposals with numerical experiments, training a discriminative model to perform handwriting recognition using a optimization procedure that could be carried out on quantum hardware, and testing the noise resilience of the trained model.

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。

↑