Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithms.
Timothée MathieuDebabrota BasuOdalric-Ambrym MaillardPublished in: Trans. Mach. Learn. Res. (2024)
Keyphrases
- lower bound
- worst case
- regret bounds
- computationally efficient
- learning algorithm
- upper bound
- theoretical analysis
- times faster
- data structure
- upper and lower bounds
- online learning
- significant improvement
- optimization problems
- constraint satisfaction problems
- np hard
- parameter tuning
- lower and upper bounds
- online algorithms
- computational complexity
- bandit problems
- regret minimization