Speaker: Kirthevasan Kandasamy
Abstract: I will discuss some recent theoretical results on Thompson sampling for Multi-armed Bandits. The discussion will be based on the following line of work,
- http://www.jmlr.org/papers/volume17/14-087/14-087.pdf
- http://djrusso.github.io/docs/Learning_to_Optimize.pdf
- https://arxiv.org/abs/1403.5556