arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.02808quant-ph
收藏

用于域自适应的量子分类器

Quantum classifiers for domain adaptation

Xi He, Feiyu Du, Mingyuan Xue, Xiaogang Du, Tao Lei, A. K. Nandi

摘要:

迁移学习(TL)是机器学习的一个重要分支,旨在利用源领域的知识完成目标领域的任务。具体而言,有效的域自适应(DA)有助于交付TL任务,其中两个域的所有数据样本分布在相同的特征空间中。本文提出了两种量子实现的DA分类器与量子加速比相比,经典的DA分类器。基于量子基本线性代数子例程(QBLAS)的分类器的一个实现可以预测具有给定数据的数量和维度的对数资源的目标域数据的标签。另一个实现有效地完成DA任务,通过变分混合量子经典过程。

英文摘要:

Transfer learning (TL), a crucial subfield of machine learning, aims to accomplish a task in the target domain with the acquired knowledge of the source domain. Specifically, effective domain adaptation (DA) facilitates the delivery of the TL task where all the data samples of the two domains are distributed in the same feature space. In this paper, two quantum implementations of the DA classifier are presented with quantum speedup compared with the classical DA classifier. One implementation, the quantum basic linear algebra subroutines (QBLAS)-based classifier, can predict the labels of the target domain data with logarithmic resources in the number and dimension of the given data. The other implementation efficiently accomplishes the DA task through a variational hybrid quantum-classical procedure.

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。

↑