Neural Constrained Combinatorial Bandits

doi:10.1109/INFOCOM53939.2023.10228958

	Neural Constrained Combinatorial Bandits
	Shangshang Wang; Simeng Bian; Xin Liu; Ziyu Shao
	2023-05
会议录名称	IEEE INFOCOM 2023
ISSN	0743-166X
卷号	2023-May
发表状态	已发表
DOI	10.1109/INFOCOM53939.2023.10228958
摘要	Constrained combinatorial contextual bandits have emerged as trending tools in intelligent systems and networks to model reward and cost signals under combinatorial decision-making. On one hand, both signals are complex functions of the context, e.g., in federated learning, training loss (negative reward) and energy consumption (cost) are nonlinear functions of edge devices' system conditions (context). On the other hand, there are cumulative constraints on costs, e.g., the accumulated energy consumption should be budgeted by energy resources. Besides, real-time systems often require such constraints to be guaranteed anytime or in each round, e.g., ensuring anytime fairness for task assignment to maintain the credibility of crowdsourcing platforms for workers. This setting imposes a challenge on how to simultaneously achieve reward maximization while subjecting to anytime cumulative constraints. To address such challenge, we propose a primal-dual algorithm (Neural-PD) whose primal component adopts multi-layer perceptrons to estimate reward and cost functions, and its dual component estimates the Lagrange multiplier with the virtual queue. By integrating neural tangent kernel theory and Lyapunov-drift techniques, we prove Neural-PD achieves a sharp regret bound and a zero constraint violation. We also show Neural-PD outperforms existing algorithms with extensive experiments on both synthetic and real-world datasets. © 2023 IEEE.
关键词	Training Crowdsourcing Energy consumption Costs Energy resources Decision making Real-time systems
会议名称	42nd IEEE International Conference on Computer Communications, INFOCOM 2023
会议地点	New York City, NY, USA
会议日期	17-20 May 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20233814771578
EI主题词	Energy resources
EI分类号	525.1 Energy Resources and Renewable Energy Issues ; 525.3 Energy Utilization ; 722.4 Digital Computers and Systems ; 723.4 Artificial Intelligence ; 911 Cost and Value Engineering ; Industrial Economics ; 912.2 Management ; 921.5 Optimization Techniques
原始文献类型	Conference article (CA)
来源库	IEEE
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/281918
专题	信息科学与技术学院信息科学与技术学院_PI研究组_邵子瑜组信息科学与技术学院_硕士生信息科学与技术学院_博士生信息科学与技术学院_PI研究组_刘鑫组
作者单位	School of Information Science and Technology, ShanghaiTech University, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Shangshang Wang,Simeng Bian,Xin Liu,et al. Neural Constrained Combinatorial Bandits[C]:Institute of Electrical and Electronics Engineers Inc.,2023.