Analysis of thompson sampling for combinatorial multi-armed bandit with probabilistically triggered arms

Simple item page
buir.contributor.authorHüyük, Alihan
buir.contributor.authorTekin, Cem
dc.contributor.authorHüyük, Alihan
dc.contributor.authorTekin, Cem
dc.coverage.spatialNaha, Okinawa, Japanen_US
dc.date.accessioned2021-02-05T06:56:48Z
dc.date.available2021-02-05T06:56:48Z
dc.date.issued2020
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 16 - 18 April 2019en_US
dc.descriptionConference name: 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019en_US
dc.description.abstractWe analyze the regret of combinatorial Thompson sampling (CTS) for the combinatorial multi-armed bandit with probabilistically triggered arms under the semi-bandit feedback setting. We assume that the learner has access to an exact optimization oracle but does not know the expected base arm outcomes beforehand. When the expected reward function is Lipschitz continuous in the expected base arm outcomes, we derive O( Pm i=1 log T /(pii)) regret bound for CTS, where m denotes the number of base arms, pi denotes the minimum non-zero triggering probability of base arm i and i denotes the minimum suboptimality gap of base arm i. We also compare CTS with combinatorial upper confidence bound (CUCB) via numerical experiments on a cascading bandit problem.en_US
dc.description.provenanceSubmitted by Evrim Ergin (eergin@bilkent.edu.tr) on 2021-02-05T06:56:48Z No. of bitstreams: 1 Analysis_of_thompson_sampling_for_combinatorial_multi-armed_bandit_with_probabilistically_triggered_arms.pdf: 624432 bytes, checksum: 5b8dcecaf0edd68004e8495c39bf8151 (MD5)en
dc.description.provenanceMade available in DSpace on 2021-02-05T06:56:48Z (GMT). No. of bitstreams: 1 Analysis_of_thompson_sampling_for_combinatorial_multi-armed_bandit_with_probabilistically_triggered_arms.pdf: 624432 bytes, checksum: 5b8dcecaf0edd68004e8495c39bf8151 (MD5) Previous issue date: 2020en
dc.identifier.urihttp://hdl.handle.net/11693/55005
dc.language.isoEnglishen_US
dc.publisherPLMRen_US
dc.source.titleProceedings of the 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019en_US
dc.titleAnalysis of thompson sampling for combinatorial multi-armed bandit with probabilistically triggered armsen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Analysis_of_thompson_sampling_for_combinatorial_multi-armed_bandit_with_probabilistically_triggered_arms.pdf
Size:
609.8 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering