Combinatorial multi-armed bandit problem with probabilistically triggered arms: a case with bounded regret

Simple item page
dc.citation.epage115en_US
dc.citation.spage111en_US
dc.contributor.authorSarıtaç, A. Ömeren_US
dc.contributor.authorTekin, Cemen_US
dc.coverage.spatialMontreal, QC, Canada
dc.date.accessioned2019-02-21T16:04:18Z
dc.date.available2019-02-21T16:04:18Z
dc.date.issued2017-11en_US
dc.departmentDepartment of Industrial Engineeringen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 14-16 Nov. 2017
dc.descriptionConference name: 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
dc.description.abstractIn this paper, we study the combinatorial multi-armed bandit problem (CMAB) with probabilistically triggered arms (PTAs). Under the assumption that the arm triggering probabilities (ATPs) are positive for all arms, we prove that a simple greedy policy, named greedy CMAB (G-CMAB), achieves bounded regret. This improves the result in previous work, which shows that the regret is O (log T) under no such assumption on the ATPs. Then, we numerically show that G-CMAB achieves bounded regret in a real-world movie recommendation problem, where the action corresponds to recommending a set of movies, arms correspond to the edges between movies and users, and the goal is to maximize the total number of users that are attracted by at least one movie. In addition to this problem, our results directly apply to the online influence maximization (OIM) problem studied in numerous prior works.
dc.description.provenanceMade available in DSpace on 2019-02-21T16:04:18Z (GMT). No. of bitstreams: 1 Bilkent-research-paper.pdf: 222869 bytes, checksum: 842af2b9bd649e7f548593affdbafbb3 (MD5) Previous issue date: 2018en
dc.identifier.doi10.1109/GlobalSIP.2017.8308614
dc.identifier.urihttp://hdl.handle.net/11693/50176
dc.language.isoEnglish
dc.publisherIEEE
dc.relation.isversionofhttps://doi.org/10.1109/GlobalSIP.2017.8308614
dc.source.title2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)en_US
dc.subjectBounded regreten_US
dc.subjectCombinatorial multi-armed banditen_US
dc.subjectOnline learningen_US
dc.subjectProbabilistically triggered armsen_US
dc.titleCombinatorial multi-armed bandit problem with probabilistically triggered arms: a case with bounded regreten_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Combinatorial_multi_armed_bandit_problem_with_probabilistically_triggered_arms_a_case_with_bounded_regret.pdf
Size:
342.89 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Industrial Engineering
Department of Electrical and Electronics Engineering