A note on the price of bandit feedback for mistake-bounded online learning.
Jesse GenesonPublished in: Theor. Comput. Sci. (2021)
Keyphrases
- online learning
- regret bounds
- higher education
- e learning
- active learning
- blended learning
- relevance feedback
- distance learning
- user feedback
- computer mediated
- distance education
- online course
- online learning environments
- feedback mechanisms
- data mining
- online algorithms
- asymptotically optimal
- random sampling
- training data
- search engine