Threshold Bandits, With and Without Censored Feedback

Jacob D. Abernethy, Kareem Amin, Ruihao Zhu

Nov-21-2025, 04:22:42 GMT–Neural Information Processing Systems

We consider the Threshold Bandit setting, a variant of the classical multi-armed bandit problem in which the reward on each round depends on a piece of side information known as a threshold value .

artificial intelligence, data mining, machine learning, (20 more...)

Neural Information Processing Systems

Nov-21-2025, 04:22:42 GMT

Conferences PDF

Country:
- Europe
  - Spain > Catalonia
    - Barcelona Province > Barcelona (0.04)
  - United Kingdom > England
    - Cambridgeshire > Cambridge (0.04)
- North America > United States
  - Massachusetts > Middlesex County
    - Cambridge (0.14)
  - Michigan > Washtenaw County
    - Ann Arbor (0.14)

Industry:
- Law > Civil Rights & Constitutional Law (0.52)

Technology:
- Information Technology
  - Artificial Intelligence > Machine Learning (1.00)
  - Data Science > Data Mining
    - Big Data (1.00)

Duplicate Docs Excel Report

Title
Threshold Bandit, With and Without Censored Feedback
Threshold Bandits, With and Without Censored Feedback

Similar Docs Excel Report more

Title	Similarity	Source
None found