arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.09899quant-phcs.LG
收藏

基于随机梯度下降的量子核对齐

Quantum Kernel Alignment with Stochastic Gradient Descent

IBM Quantum, IBM Research Europe – Zurich(IBM量子,IBM欧洲研究院苏黎世分部);IBM Quantum, IBM T.J. Watson Research Center(IBM量子,IBM托马斯·J·沃森研究中心)

Gian Gentinetta, David Sutter, Christa Zoufal, Bryce Fuller, Stefan Woerner

AI总结:

本文将基于随机梯度下降的 Pegasos 算法扩展到量子支持向量机,实现SVM训练与量子核对齐同步进行,实验表明其精度更高且尤其适合非平稳数据。

摘要:

量子支持向量机有潜力在解决某些机器学习问题时实现量子加速。实现这一点的关键挑战在于为给定数据集找到良好的量子核——这一任务称为核对齐。在本文中,我们使用 Pegasos 算法研究该问题,该算法利用随机梯度下降来求解支持向量机优化问题。我们将 Pegasos 扩展到量子情形,并展示其在核对齐方面的有效性。不同于以往通过在外部优化循环中训练 QSVM 来执行核对齐的工作,我们表明使用 Pegasos 可以同时训练支持向量机并对齐核。实验表明,该方法能够以高精度对齐量子特征映射,并且优于现有量子核对齐技术。具体而言,我们证明 Pegasos 对非平稳数据特别有效,而非平稳数据是现实应用中的一项重要挑战。

英文摘要:

Quantum support vector machines have the potential to achieve a quantum speedup for solving certain machine learning problems. The key challenge for doing so is finding good quantum kernels for a given data set -- a task called kernel alignment. In this paper we study this problem using the Pegasos algorithm, which is an algorithm that uses stochastic gradient descent to solve the support vector machine optimization problem. We extend Pegasos to the quantum case and and demonstrate its effectiveness for kernel alignment. Unlike previous work which performs kernel alignment by training a QSVM within an outer optimization loop, we show that using Pegasos it is possible to simultaneously train the support vector machine and align the kernel. Our experiments show that this approach is capable of aligning quantum feature maps with high accuracy, and outperforms existing quantum kernel alignment techniques. Specifically, we demonstrate that Pegasos is particularly effective for non-stationary data, which is an important challenge in real-world applications.

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。

↑