Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
–Neural Information Processing Systems
In linear bandits, how can a learner effectively learn when facing corrupted rewards?
Neural Information Processing Systems
Nov-15-2025, 07:08:16 GMT
- Country:
- North America > United States
- Virginia (0.04)
- California > Alameda County
- Berkeley (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Asia > Middle East
- North America > United States
- Genre:
- Research Report > Experimental Study (0.92)
- Technology: