南方科技大学知识苑(SUSTech KC): Symmetry-guided gradient descent for quantum neural networks

题名	Symmetry-guided gradient descent for quantum neural networks
作者	Bian, Kaiming 1,2 ; Zhang, Shitao1 ; Meng, Fei 3; Zhang, Wen 4; Dahlsten, Oscar1,3,5
通讯作者	Meng, Fei
发表日期	2024-08-05
DOI	10.1103/PhysRevA.110.022406
发表期刊	PHYSICAL REVIEW A 影响因子和分区
ISSN	2469-9926
EISSN	2469-9934
卷号	110 期号:2
摘要	Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise mathematical form. We design two ways to adopt the constraints into the cost function, thereby shaping the cost landscape in favor of parameter choices, which respect the given symmetry. Unlike methods that alter the neural network circuit Ansatz to impose symmetry, our method only changes the classical postprocessing of gradient descent, which is simpler to implement. We call the method symmetry-guided gradient descent (SGGD). We illustrate SGGD in entanglement classification of Werner states and in two classification tasks in a two-dimensional feature space. In both cases, the results show that SGGD can accelerate the training, improve the generalization ability, and remove vanishing gradients, especially when the training data is biased.
相关链接	[来源记录]
收录类别	SCI ; EI
语种	英语
学校署名	第一
资助项目	National Natural Science Foundation of China["12050410246","1200509","12050410245"] ; City University of Hong Kong[9610623]
WOS研究方向	Optics ; Physics
WOS类目	Optics ; Physics, Atomic, Molecular & Chemical
WOS记录号	WOS:001285582000005
出版者	AMER PHYSICAL SOC
ESI学科分类	PHYSICS
来源库	Web of Science
引用统计
成果类型	期刊论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/803295
专题	量子科学与工程研究院南方科技大学理学院_物理系
作者单位	1.Southern Univ Sci & Technol, Shenzhen Inst Quantum Sci & Engn, Shenzhen 518055, Peoples R China 2.Southern Univ Sci & Technol, Dept Phys, Shenzhen 518055, Peoples R China 3.City Univ Hong Kong, Dept Phys, Kowloon, Tat Chee Ave, Hong Kong, Peoples R China 4.Huawei Technol Co Ltd, HiSilicon Res, Shenzhen 518129, Peoples R China 5.Southern Univ Sci & Technol, Inst Nanosci & Applicat, Shenzhen 518055, Peoples R China
第一作者单位	量子科学与工程研究院; 物理系
第一作者的第一单位	量子科学与工程研究院
推荐引用方式 GB/T 7714	Bian, Kaiming,Zhang, Shitao,Meng, Fei,et al. Symmetry-guided gradient descent for quantum neural networks[J]. PHYSICAL REVIEW A,2024,110(2).
APA	Bian, Kaiming,Zhang, Shitao,Meng, Fei,Zhang, Wen,&Dahlsten, Oscar.(2024).Symmetry-guided gradient descent for quantum neural networks.PHYSICAL REVIEW A,110(2).
MLA	Bian, Kaiming,et al."Symmetry-guided gradient descent for quantum neural networks".PHYSICAL REVIEW A 110.2(2024).