Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions.
Saeed MasoudianYevgeny SeldinPublished in: COLT (2021)
Keyphrases
- improved algorithm
- optimization algorithm
- learning algorithm
- preprocessing
- times faster
- computational complexity
- computational cost
- dynamic programming
- detection algorithm
- experimental evaluation
- matching algorithm
- genetic algorithm
- high accuracy
- k means
- stochastic systems
- convergence rate
- clustering method
- regret bounds
- multi armed bandit
- worst case
- optimal solution
- cost function
- particle swarm optimization
- np hard
- monte carlo
- neural network
- objective function
- stochastic simulation
- multi agent
- significant improvement
- tree structure
- ant colony optimization
- least squares
- linear programming
- segmentation algorithm
- theoretical analysis
- computationally efficient