PAC-Bayesian Analysis of Contextual Bandits François Laviolette

Mar-15-2024, 02:44:14 GMT–Neural Information Processing Systems

We derive an instantaneous (per-round) data-dependent regret bound for stochastic multiarmed bandits with side information (also known as contextual bandits).

algorithm, information, side information, (16 more...)

Neural Information Processing Systems

Mar-15-2024, 02:44:14 GMT

Conferences PDF

Add feedback

Country:
- North America > Canada
  - Quebec (0.04)
- Europe
  - United Kingdom > England
    - Greater London > London (0.04)
  - Germany > Baden-Württemberg
    - Tübingen Region > Tübingen (0.14)
  - Austria > Styria
    - Leoben (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Computational Learning Theory (0.46)