Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
–Neural Information Processing Systems
We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty"
Neural Information Processing Systems
Oct-9-2025, 01:04:32 GMT
- Country:
- Asia > Malaysia
- Europe
- Denmark > Southern Denmark (0.04)
- Germany > Hesse
- Darmstadt Region > Darmstadt (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- North America > Canada
- Alberta (0.14)
- Industry:
- Education (0.45)
- Technology: