Contextual Linear Optimization with Bandit Feedback
–Neural Information Processing Systems
We show a fast-rate regret bound for IERM that allows for misspecified model classes and flexible choices of the optimization estimate, and we develop computationally tractable surrogate losses.
Neural Information Processing Systems
Oct-9-2025, 22:25:15 GMT
- Country:
- Asia > China (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Genre:
- Research Report > New Finding (0.67)
- Technology: