Thompson Sampling with Information Relaxation Penalties Seungki Min Columbia Business School Costis Maglaras Columbia Business School Ciamac C. Moallemi Columbia Business School

Aug-20-2025, 07:27:44 GMT–Neural Information Processing Systems

We consider a finite-horizon multi-armed bandit (MAB) problem in a Bayesian setting, for which we propose an information relaxation sampling framework.

artificial intelligence, data mining, machine learning, (16 more...)

Neural Information Processing Systems

Aug-20-2025, 07:27:44 GMT

Conferences PDF

Country:
- North America > Canada (0.04)

Industry:
- Health & Medicine (1.00)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Learning Graphical Models
      - Directed Networks > Bayesian Learning (0.68)
    - Representation & Reasoning > Uncertainty
      - Bayesian Inference (0.68)
  - Data Science > Data Mining (0.66)

Duplicate Docs Excel Report

Title
e5b294b70c9647dcf804d7baa1903918-Paper.pdf

Similar Docs Excel Report more

Title	Similarity	Source
None found