Aging wireless bandits: regret analysis and order-optimal learning algorithm

Simple item page
buir.contributor.authorAtay, Eray Unsal
dc.citation.epage8en_US
dc.citation.spage1en_US
dc.contributor.authorAtay, Eray Unsal
dc.contributor.authorKadota, Igor
dc.contributor.authorModiano, Eytan
dc.coverage.spatialPhiladelphia, PA, USAen_US
dc.date.accessioned2022-02-03T10:06:26Z
dc.date.available2022-02-03T10:06:26Z
dc.date.issued2021-11-13
dc.descriptionConference Name: 2021 19th International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt)en_US
dc.descriptionDate of Conference: 18-21 October 2021en_US
dc.description.abstractWe consider a single-hop wireless network with sources transmitting time-sensitive information to the destination over multiple unreliable channels. Packets from each source are generated according to a stochastic process with known statistics and the state of each wireless channel (ON/OFF) varies according to a stochastic process with unknown statistics. The reliability of the wireless channels is to be learned through observation. At every time-slot, the learning algorithm selects a single pair (source, channel) and the selected source attempts to transmit its packet via the selected channel. The probability of a successful transmission to the destination depends on the reliability of the selected channel. The goal of the learning algorithm is to minimize the Age-of-Information (AoI) in the network over T time-slots. To analyze its performance, we introduce the notion of AoI-regret, which is the difference between the expected cumulative AoI of the learning algorithm under consideration and the expected cumulative AoI of a genie algorithm that knows the reliability of the channels a priori. The AoI-regret captures the penalty incurred by having to learn the statistics of the channels over the T time-slots. The results are two-fold: first, we consider learning algorithms that employ well-known solutions to the stochastic multi-armed bandit problem (such as ϵ-Greedy, Upper Confidence Bound, and Thompson Sampling) and show that their AoI-regret scales as Θ(log T); second, we develop a novel learning algorithm and show that it has O(1) regret. To the best of our knowledge, this is the first learning algorithm with bounded AoI-regret.en_US
dc.identifier.doi10.23919/WiOpt52861.2021.9589673en_US
dc.identifier.eisbn978-3-903176-37-9
dc.identifier.isbn978-1-6654-3292-4
dc.identifier.urihttp://hdl.handle.net/11693/76985
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://dx.doi.org/10.23919/WiOpt52861.2021.9589673en_US
dc.source.titleInternational Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)en_US
dc.subjectAge of Informationen_US
dc.subjectWireless networksen_US
dc.subjectRegreten_US
dc.subjectMulti-armed banditsen_US
dc.subjectLearningen_US
dc.titleAging wireless bandits: regret analysis and order-optimal learning algorithmen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Aging_Wireless_Bandits_Regret_Analysis_and_Order-Optimal_Learning_Algorithm.pdf
Size:
1.05 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Electrical and Electronics Engineering