CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption.
Shubhada AgrawalTimothée MathieuDebabrota BasuOdalric-Ambrym MaillardPublished in: CoRR (2023)
Keyphrases
- lower and upper bounds
- regret bounds
- lower bound
- upper bound
- multi armed bandit
- upper and lower bounds
- expert advice
- branch and bound
- branch and bound algorithm
- worst case
- stochastic systems
- multi armed bandits
- np hard
- multi armed bandit problems
- valid inequalities
- lagrangian relaxation
- online learning
- online convex optimization
- linear regression
- cutting plane
- objective function
- linear programming relaxation
- linear programming
- simulated annealing
- search algorithm
- optimal solution