Regret Minimisation in Multinomial Logit Bandits.
Aadirupa SahaAditya GopalanPublished in: CoRR (2019)
Keyphrases
- multinomial logit
- regret bounds
- multi armed bandit problems
- multi armed bandit
- multi armed bandits
- bandit problems
- feature selection
- online learning
- lower bound
- linear regression
- expert advice
- upper bound
- confidence bounds
- stochastic systems
- reinforcement learning
- regret minimization
- binary classification
- loss function
- data mining
- weighted majority
- machine learning
- data sets