Concepedia

Thompson Sampling

Thompson Sampling is a probabilistic treatment assignment method in the exploration-exploitation tradeoff that allocates interventions according to their posterior probability of being optimal, distinguishing itself by explicitly balancing learning and decision-making through Bayesian updating.

230

Publications

11K

Citations

483

Authors

197

Institutions

Publications per year

2017–2026

160

Variants

Probability Matching

Parents

Publications

230

An Empirical Evaluation of Thompson Sampling

Olivier Chapelle, Lihong Li · 2011 · 1K citations

, , +10

Analysis of Thompson Sampling for the multi-armed bandit problem

Shipra Agrawal, Navin Goyal · arXiv (Cornell University) · 2011 · 743 citations · Full text

, , +14

Thompson Sampling for Contextual Bandits with Linear Payoffs

Shipra Agrawal, Navin Goyal · arXiv (Cornell University) · 2012 · 548 citations · Full text

, , +17

Learning to Optimize via Posterior Sampling

Daniel Russo, Benjamin Van Roy · Mathematics of Operations Research · 2014 · 536 citations

, , +17

A Tutorial on Thompson Sampling

Daniel Russo, Benjamin Van Roy, Abbas Kazerouni et al. · Foundations and Trends® in Machine Learning · 2018 · 519 citations

, , +9

1–5 of 230

Authors

483

  1. BV
    Benjamin Van Roy

    Stanford University, United States

    14 publications · 1.4K citations

    13

    h-index

  2. SA
    Shipra Agrawal

    Columbia University, United States

    9 publications · 2.2K citations

    9

    h-index

  3. ZW
    Zheng Wen

    Adobe Systems (United States), United States

    6 publications · 640 citations

    6

    h-index

  4. BK
    Branislav Kveton

    Adobe Systems (United States), United States

    6 publications · 211 citations

    6

    h-index

  5. DR
    Daniel Russo

    Columbia University, United States

    6 publications · 1.2K citations

    6

    h-index

1–5 of 483

Institutions

197

  1. Stanford University

    Stanford, United States

    11 h-index

    24 publications

    2.6K citations

  2. Google (United States)

    Mountain View, United States

    10 h-index

    19 publications

    873 citations

  3. Microsoft (United States)

    Redmond, United States

    8 h-index

    14 publications

    883 citations

  4. Columbia University

    New York, United States

    6 h-index

    12 publications

    924 citations

  5. The University of Tokyo

    Tokyo, Japan

    6 h-index

    12 publications

    530 citations

  6. Carnegie Mellon University

    Pittsburgh, United States

    6 h-index

    21 publications

    570 citations

  7. Vrije Universiteit Brussel

    Brussels, Belgium

    5 h-index

    19 publications

    275 citations

  8. National University of Singapore

    Singapore, Singapore

    5 h-index

    9 publications

    347 citations

1–8 of 197

Venues

  1. arXiv (Cornell University)

    Repository · 79 publications · 4.2K citations

    28

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 8 publications · 302 citations

    8

    h-index

  3. Neural Information Processing Systems

    Conference · 6 publications · 227 citations

    6

    h-index

  4. Conference on Learning Theory

    Conference · 4 publications · 93 citations

    4

    h-index

  5. International Conference on Machine Learning

    Conference · 3 publications · 48 citations

    3

    h-index

1–5