Master Thesis Presentation

​Emelie Lööf: Cluster KL-UCB: Optimism for the Best, Pessimism for the Rest

The project present an allocation strategy for the stochastic multi armed bandit when considering instances with a clustered structure. Using the architecture of the KL-UCB policy as a source of inspiration, an algorithm which exploits and takes advantage from a clustered structure is derived. Firstly, encouraged by previous work related to the subject, a multi-level structure approach will constitute as an initial examination. Secondly, the Cluster KL-UCB policy will be derived and evaluated considering three different approaches. It will be shown, both theoretically and empirically, that adapting to a clustered environment improves the performance compared to its non cluster-adapting ancestor. Both upper and lower bounds on the regret will be provided in order to theoretically ensure the performance of the algorithm. Lastly, a number of empirical experiments will be performed in order to further ensure the performance and validate the theoretical results.
​Opponents: Victor López Juan och Rode Grönkvist
Examiner: Johan Jonasson
Category Student project presentation
Location: MV:L14, Chalmers tvärgata 3
Starts: 31 May, 2022, 10:00
Ends: 31 May, 2022, 11:00

Page manager Published: Thu 26 May 2022.