Sharp regret bounds for empirical Bayes and compound decision problems.
Yury PolyanskiyYihong WuPublished in: CoRR (2021)
Keyphrases
- decision problems
- empirical bayes
- regret bounds
- influence diagrams
- lower bound
- online learning
- linear regression
- multi armed bandit
- decision model
- utility function
- computational complexity
- optimal policy
- np hard
- upper bound
- bayesian decision problems
- online convex optimization
- markov random field
- bandit problems
- linear predictors
- message passing