Online Learning for Network Optimization under Unknown Models

被引：0

作者：

Zhai, Yixuan ^{[1
]}

Zhao, Qing ^{[1
]}

机构：

[1] Univ Calif Davis, Elect & Comp Engn, Davis, CA 95616 USA

来源：

2013 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP) | 2013年

关键词：

Bandit problem; shortest path; best linear unbiased estimator; ALLOCATION;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

We consider the shortest path problem in a communication network with random link costs drawn from unknown distributions. A realization of the total end-to-end cost is obtained when a path is selected for communication. The objective is an online learning algorithm that minimizes the total expected communication cost in the long run. The problem is formulated as a multi-armed bandit problem with dependent arms, and an algorithm based on basis-based learning integrated with a Best Linear Unbiased Estimator (BLUE) is developed.

引用

页码：575 / 578

页数：4

共 50 条

[21] Online Learning for Unknown Partially Observable MDPs
Jafarnia-Jahromi, Mehdi
Jain, Rahul
Nayyar, Ashutosh
[J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
[22] Online Learning of Feasible Strategies in Unknown Environments
Paternain, Santiago
Ribeiro, Alejandro
[J]. 2015 AMERICAN CONTROL CONFERENCE (ACC), 2015, : 4231 - 4238
[23] Online Learning of Optimal Strategies in Unknown Environments
Paternain, Santiago
Ribeiro, Alejandro
[J]. 2015 54TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2015, : 3951 - 3958
[24] Topological optimization models for reliable communication network under fuzziness
Gao, Xiaofeng
Zhou, Jian
[J]. PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON INFORMATION AND MANAGEMENT SCIENCES, 2006, 5 : 383 - 388
[25] Adaptive open set domain generalization network: Learning to diagnose unknown faults under unknown working conditions
Zhao, Chao
Shen, Weiming
[J]. RELIABILITY ENGINEERING & SYSTEM SAFETY, 2022, 226
[26] Learning and optimization under epistemic uncertainty with Bayesian hybrid models
Eugene, Elvis A.
Jones, Kyla D.
Gao, Xian
Wang, Jialu
Dowling, Alexander W.
[J]. COMPUTERS & CHEMICAL ENGINEERING, 2023, 179
[27] CARAVAN: Practical Online Learning of In-Network ML Models with Labeling Agents
Zhang, Qizheng
Imran, Ali
Bardhi, Enkeleda
Swamy, Tushar
Zhang, Nathan
Shahbaz, Muhammad
Olukotun, Kunle
[J]. PROCEEDINGS OF THE 18TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, OSDI 2024, 2024, : 325 - 345
[28] Convergence Properties of an Online Learning Algorithm in Neural Network Models of Complex Systems
Azarskov, V. N.
Nikolaienko, S. A.
Zhiteckii, L. S.
[J]. 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON ACTUAL PROBLEMS OF UNMANNED AIR VEHICLES DEVELOPMENTS (APUAVD), 2013, : 89 - 92
[29] Online Learning for Constrained Assortment Optimization Under Markov Chain Choice Model
Li, Shukai
Luo, Qi
Huang, Zhiyuan
Shi, Cong
[J]. OPERATIONS RESEARCH, 2024, : 1 - 30
[30] Online Optimizing Multi-user Interference Network Utility with Unknown CSI under Budget Constraint
Chen, Yuchao
Wang, Jintao
Zhang, Qining
Gao, Feifei
Song, Jian
[J]. 2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, : 1623 - 1628

← 1 2 3 4 5 →