Asymptotically optimal strategies for online prediction with history-dependent experts.
Jeff CalderNadejda DrenskaPublished in: CoRR (2020)
Keyphrases
- optimal strategy
- prediction accuracy
- decision problems
- online learning
- monte carlo
- expected utility
- prediction algorithm
- prediction model
- real time
- historical information
- machine learning
- mathematical models
- case study
- computational model
- prediction error
- worst case
- expected cost
- e learning
- artificial intelligence
- expert advice