Regret to the Best vs. Regret to the Average.
Eyal Even-DarMichael J. KearnsYishay MansourJennifer WortmanPublished in: COLT (2007)
Keyphrases
- lower bound
- online learning
- expert advice
- regret minimization
- loss function
- confidence bounds
- worst case
- regret bounds
- weighted majority
- database
- bandit problems
- minimax regret
- binary classification
- evolutionary algorithm
- multi armed bandit problems
- online convex optimization
- standard deviation
- pairwise
- data structure
- similarity measure
- learning algorithm