Logarithmic Regret from Sublinear Hints.
Aditya BhaskaraAshok CutkoskyRavi KumarManish PurohitPublished in: NeurIPS (2021)
Keyphrases
- regret bounds
- worst case
- online learning
- lower bound
- space complexity
- expert advice
- loss function
- confidence bounds
- bandit problems
- online convex optimization
- regret minimization
- upper bound
- linear regression
- databases
- minimax regret
- weighted majority
- data structure
- game theory
- multiscale
- bayesian networks
- multi armed bandit
- similarity measure
- machine learning
- upper confidence bound
- database