On the price of exact truthfulness in incentive-compatible online learning with bandit feedback: A regret lower bound for WSU-UX.
Ali MortazaviJunhao LinNishant A. MehtaPublished in: CoRR (2024)
Keyphrases
- regret bounds
- online learning
- incentive compatible
- mechanism design
- lower bound
- upper bound
- game theory
- online convex optimization
- adverse selection
- incomplete information
- online algorithms
- e learning
- incentive compatibility
- multi armed bandit
- user experience
- nash equilibrium
- linear regression
- worst case
- rational agents
- auction mechanisms
- special case
- social choice
- optimal solution
- np hard
- machine learning
- intelligent agents
- artificial intelligence