CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption.
Shubhada AgrawalTimothée MathieuDebabrota BasuOdalric-Ambrym MaillardPublished in: ALT (2024)
Keyphrases
- lower and upper bounds
- regret bounds
- lower bound
- upper bound
- upper and lower bounds
- multi armed bandit
- stochastic systems
- expert advice
- worst case
- branch and bound algorithm
- np hard
- branch and bound
- lagrangian relaxation
- optimal solution
- online learning
- objective function
- valid inequalities
- multi armed bandit problems
- multi armed bandits
- linear programming relaxation
- linear regression
- online convex optimization
- itemsets
- search algorithm
- real world