A Multiple-Play Bandit Algorithm Applied to Recommender Systems.
Jonathan LouëdecMax ChevalierJosiane MotheAurélien GarivierSébastien GerchinovitzPublished in: FLAIRS Conference (2015)
Keyphrases
- times faster
- recommender systems
- learning algorithm
- theoretical analysis
- dynamic programming
- data sets
- np hard
- cost function
- significant improvement
- k means
- optimal solution
- preprocessing
- computational cost
- probabilistic model
- worst case
- high accuracy
- linear programming
- objective function
- recognition algorithm
- improved algorithm
- filtering algorithm
- matching algorithm
- detection algorithm
- segmentation algorithm
- evolutionary algorithm
- computational complexity
- neural network