Fast variational quantum algorithms for training neural networks and solving convex optimizations

doi:10.1103/PhysRevA.99.042325

CSpace

	Fast variational quantum algorithms for training neural networks and solving convex optimizations
	Shao, Changpeng
	2019-04-17
发表期刊	PHYSICAL REVIEW A
ISSN	2469-9926
卷号	99 期号:4 页码:10
摘要	Variational hybrid quantum classical algorithms to optimizations are important applications for near-term quantum computing. This paper proposes two quantum algorithms (the second one is variational) for training neural networks. Both of them obtain exponential speedup at the number of samples and polynomial speedup at the dimension of the samples over classical training algorithms. Moreover, the proposed quantum algorithms return the classical information of the training weight so that the outputs can be used directly to solve other problems. For practicality, we draw the quantum circuits to implement the two algorithms. Finally, as an inspiration, we show how to apply the variational algorithm to achieve speedup at the number of constraints in solving convex optimization problems.
DOI	10.1103/PhysRevA.99.042325
语种	英语
资助项目	National Natural Science Foundation of China[11671388] ; CAS Frontier Key Project[QYZDJ-SSW-SYS022]
WOS研究方向	Optics ; Physics
WOS类目	Optics ; Physics, Atomic, Molecular & Chemical
WOS记录号	WOS:000465146100003
出版者	AMER PHYSICAL SOC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/34590
专题	中国科学院数学与系统科学研究院
通讯作者	Shao, Changpeng
作者单位	Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Shao, Changpeng. Fast variational quantum algorithms for training neural networks and solving convex optimizations[J]. PHYSICAL REVIEW A,2019,99(4):10.
APA	Shao, Changpeng.(2019).Fast variational quantum algorithms for training neural networks and solving convex optimizations.PHYSICAL REVIEW A,99(4),10.
MLA	Shao, Changpeng."Fast variational quantum algorithms for training neural networks and solving convex optimizations".PHYSICAL REVIEW A 99.4(2019):10.