🏢 Hokkaido University
No-Regret M${}^{
atural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
·1615 words·8 mins·
loading
·
loading
AI Generated
AI Theory
Optimization
🏢 Hokkaido University
This paper reveals efficient stochastic bandit algorithms for maximizing M-concave functions and proves NP-hardness for adversarial full-information settings.