Presentation 2020-03-11
Regret analysis of Thompson sampling using a general beta prior
Yuto Kawamura, Toshiyuki Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For Bernoulli bandits, the asymptotic optimality of Thompson sampling with the uniform prior in terms of the regret has already been established. However, regret analysis of Thompson sampling with other priors has not been well studied. In this paper, we perform regret analysis of Thompson sampling with the general beta prior and prove its asymptotic optimality.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Bernoulli bandit / Thompson sampling / regret / asymptotic optimality
Paper # IBISML2019-49
Date of Issue 2020-03-03 (IBISML)

Conference Information
Committee IBISML
Conference Date 2020/3/10(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyoto University
Topics (in Japanese) (See Japanese page)
Topics (in English) Machine learning, etc.
Chair Hisashi Kashima(Kyoto Univ.)
Vice Chair Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST)
Assistant Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Regret analysis of Thompson sampling using a general beta prior
Sub Title (in English)
Keyword(1) Bernoulli bandit
Keyword(2) Thompson sampling
Keyword(3) regret
Keyword(4) asymptotic optimality
1st Author's Name Yuto Kawamura
1st Author's Affiliation Kyoto University(Kyoto Univ.)
2nd Author's Name Toshiyuki Tanaka
2nd Author's Affiliation Kyoto University(Kyoto Univ.)
Date 2020-03-11
Paper # IBISML2019-49
Volume (vol) vol.119
Number (no) IBISML-476
Page pp.pp.107-112(IBISML),
#Pages 6
Date of Issue 2020-03-03 (IBISML)