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: AISTATS (2024)
Keyphrases
- regret bounds
- online learning
- incentive compatible
- mechanism design
- lower bound
- adverse selection
- online convex optimization
- e learning
- online algorithms
- user experience
- upper bound
- incomplete information
- game theory
- multi armed bandit
- nash equilibrium
- social choice
- incentive compatibility
- active learning
- machine learning
- combinatorial auctions
- np hard
- rational agents
- auction mechanisms
- objective function
- artificial intelligence
- decision making
- bandit problems
- optimal solution
- linear programming