Sub-sampling for Efficient Non-Parametric Bandit Exploration
–Neural Information Processing Systems
In this paper, we propose the first re-sampling based algorithm that is asymptotically optimal for several classes of possibly un-bounded parametric distributions.
Neural Information Processing Systems
Nov-13-2025, 20:47:16 GMT
- Country:
- Asia > Russia (0.04)
- Europe
- France > Hauts-de-France
- Russia (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- North America > Canada (0.04)
- Genre:
- Research Report (0.68)
- Technology: