A survey on online learning methods: Thompson sampling and others

DOI10.15960/J.CNKI.ISSN.1007-6093.2017.04.006MaRDI QIDQ3176079zbMATH OpenFDO

Authors Simai He, Yu Jia Jin, Hua Wang, Dongdong Ge

Publication date 18 July 2018

Full work available at URL https://doi.org/10.15960/J.CNKI.ISSN.1007-6093.2017.04.006

zbMATH Keywords

multi-armed banditonline learningupper confidence boundonline convex optimizationThompson sampling

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Convex programming (90C25) Sampling theory, sample surveys (62D05) Stopping times; optimal stopping problems; gambling theory (60G40)

Recommendations

• A Tutorial on Thompson Sampling
• An information-theoretic analysis of Thompson sampling
• Multi-Armed Bandits: Theory and Applications to Online Learning in Networks
• Learning to optimize via posterior sampling
• Near-optimal regret bounds for Thompson sampling

Cited in

(1)

• A Survey of Preference-Based Online Learning with Bandit Algorithms

This page was built for publication: A survey on online learning methods: Thompson sampling and others

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3176079)