Contextual bandits with surrogate losses: Margin bounds and efficient algorithms
Dylan J. Foster, Akshay Krishnamurthy
–Neural Information Processing Systems
We use surrogate losses to obtain several new regret bounds and new algorithms for contextual bandit learning.
Neural Information Processing Systems
Nov-20-2025, 23:18:16 GMT
- Country:
- Asia > Middle East
- Europe > United Kingdom
- England
- Cambridgeshire > Cambridge (0.04)
- Oxfordshire > Oxford (0.04)
- England
- North America > Canada
- Industry:
- Education > Educational Setting > Online (0.47)
- Technology: