Regret, stability & fairness in matching markets with bandit learners.
Sarah Huiyi CenDevavrat ShahPublished in: AISTATS (2022)
Keyphrases
- bandit problems
- matching algorithm
- upper confidence bound
- learning environment
- regret bounds
- online learning
- learning systems
- game theory
- e learning
- multi armed bandit problems
- learning strategies
- collaborative learning
- learning process
- multi armed bandit
- keypoints
- learning materials
- graph matching
- pattern matching
- learning experience
- worst case
- shape matching
- electronic commerce
- pairwise
- language learning
- image matching
- concept maps
- matching process
- stability analysis
- social learning
- mobile devices
- markov chain
- feature points
- lower bound
- learning algorithm