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
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
收藏
页码:575 / 578
页数:4
相关论文
共 50 条
  • [1] Stochastic Online Learning under Unknown Time-Varying Models
    Tehrani, Pouya
    Zhao, Qing
    [J]. 2012 CONFERENCE RECORD OF THE FORTY SIXTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS (ASILOMAR), 2012, : 1046 - 1050
  • [2] AN ONLINE LEARNING APPROACH TO THROUGHPUT OPTIMIZATION IN WIRELESS NETWORKS UNDER DYNAMIC AND UNKNOWN INTERFERENCE CONDITIONS
    Annavajjala, Ramesh
    Mangoubi, Rami S.
    Yu, Christopher C.
    Zagami, James M.
    [J]. 2015 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2015,
  • [3] Online learning of multiple perceptual models for navigation in unknown terrain
    Grudic, Greg
    Mulligan, Jane
    Otte, Michael
    Bates, Adam
    [J]. FIELD AND SERVICE ROBOTICS: RESULTS OF THE 6TH INTERNATIONAL CONFERENCE, 2008, 42 : 411 - 420
  • [4] Online Learning for Characterizing Unknown Environments in Ground Robotic Vehicle Models
    Koppel, Alec
    Fink, Jonathan
    Warnell, Garrett
    Stump, Ethan
    Ribeiro, Alejandro
    [J]. 2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), 2016, : 626 - 633
  • [5] ONLINE LEARNING AND OPTIMIZATION OF MARKOV JUMP LINEAR MODELS
    Baltaoglu, Sevi
    Tong, Lang
    Zhao, Qing
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 2289 - 2293
  • [6] An Online Learning Approach to Network Application Optimization with Guarantee
    Cai, Kechao
    Liu, Xutong
    Chen, Yu-Zhen Janice
    Lui, John C. S.
    [J]. IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2018), 2018, : 2015 - 2023
  • [7] DISTRIBUTED ONLINE LEARNING OF THE SHORTEST PATH UNDER UNKNOWN RANDOM EDGE WEIGHTS
    Tehrani, Pouya
    Zhao, Qing
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 3138 - 3142
  • [8] Cellular Network Configuration via Online Learning and Joint Optimization
    Guo, Xueying
    Trimponias, George
    Wang, Xiaoxiao
    Chen, Zhitang
    Geng, Yanhui
    Liu, Xin
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2017, : 1295 - 1300
  • [9] Online Learning with an Unknown Fairness Metric
    Gillen, Stephen
    Jung, Christopher
    Kearns, Michael
    Roth, Aaron
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [10] Online Learning in Unknown Markov Games
    Tian, Yi
    Wang, Yuanhao
    Yu, Tiancheng
    Sra, Suvrit
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139 : 7290 - 7300