Regret to the best vs. regret to the average.
Eyal Even-DarMichael J. KearnsYishay MansourJennifer WortmanPublished in: Mach. Learn. (2008)
Keyphrases
- online learning
- expert advice
- lower bound
- confidence bounds
- regret minimization
- online convex optimization
- regret bounds
- bandit problems
- minimax regret
- loss function
- upper confidence bound
- information retrieval
- game theory
- worst case
- dynamic programming
- binary classification
- weighted majority
- standard deviation
- nash equilibrium
- real time
- support vector
- genetic algorithm
- neural network