Tighter Regret Bounds for Influence Maximization and Other Combinatorial Semi-Bandits with Probabilistically Triggered Arms.
Qinshi WangWei ChenPublished in: CoRR (2017)
Keyphrases
- regret bounds
- influence maximization
- lower bound
- upper bound
- greedy algorithm
- multi armed bandit
- multi armed bandits
- social networks
- diffusion model
- viral marketing
- worst case
- online social networks
- online learning
- linear regression
- objective function
- social network analysis
- np hard
- social media
- information diffusion
- reinforcement learning
- computer vision
- maximum entropy