Learning Convex Optimization Models

doi:10.1109/JAS.2021.1004075

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Learning Convex Optimization Models
	Akshay Agrawal; Shane Barratt; Stephen Boyd
刊名	IEEE/CAA Journal of Automatica Sinica
	2021
卷号	8 期号:8 页码:1355-1364
关键词	Convex optimization differentiable optimization machine learning
ISSN号	2329-9266
DOI	10.1109/JAS.2021.1004075
英文摘要	A convex optimization model predicts an output from an input by solving a convex optimization problem. The class of convex optimization models is large, and includes as special cases many well-known models like linear and logistic regression. We propose a heuristic for learning the parameters in a convex optimization model given a dataset of input-output pairs, using recently developed methods for differentiating the solution of a convex optimization problem with respect to its parameters. We describe three general classes of convex optimization models, maximum a posteriori (MAP) models, utility maximization models, and agent models, and present a numerical experiment for each.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44588]
专题	自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Akshay Agrawal,Shane Barratt,Stephen Boyd. Learning Convex Optimization Models[J]. IEEE/CAA Journal of Automatica Sinica,2021,8(8):1355-1364.
APA	Akshay Agrawal,Shane Barratt,&Stephen Boyd.(2021).Learning Convex Optimization Models.IEEE/CAA Journal of Automatica Sinica,8(8),1355-1364.
MLA	Akshay Agrawal,et al."Learning Convex Optimization Models".IEEE/CAA Journal of Automatica Sinica 8.8(2021):1355-1364.