期刊
QUANTUM SCIENCE AND TECHNOLOGY
卷 7, 期 2, 页码 -出版社
IOP Publishing Ltd
DOI: 10.1088/2058-9565/ac4f30
关键词
quantum machine learning; sample complexity; PAC learnable; quantum circuit
资金
- start-up fund from Tsinghua University [53330300320]
- National Natural Science Foundation of China [12075128]
- Shanghai Qi Zhi Institute
This article proves that physical quantum circuits can be learned through empirical risk minimization on a quantum computer, and provides valuable guidance for the development of quantum machine learning in both theory and practice.
Quantum computers hold unprecedented potentials for machine learning applications. Here, we prove that physical quantum circuits are probably approximately correct learnable on a quantum computer via empirical risk minimization: to learn a parametric quantum circuit with at most n(c) gates and each gate acting on a constant number of qubits, the sample complexity is bounded by O(n(c+1)). In particular, we explicitly construct a family of variational quantum circuits with O(n(c+1)) elementary gates arranged in a fixed pattern, which can represent all physical quantum circuits consisting of at most n` elementary gates. Our results provide a valuable guide for quantum machine learning in both theory and practice.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据