When: January 17, 2014 from 11AM to noon
Where: room B21
Speaker: Claudio Gentile
Title: Online Clustering of Bandits (in a Social Network)
Abstract: Bandit algorithms have become a standard tool for facing the the so-called exploration-exploitation
dilemma that naturally arises in learning problems with partial information. Recommendation systems
are one of the best applications where such algorithmic solutions may be of relevance. In many cases,
these applications have social components (either explicit or hidden), whose integration in the bandit
algorithms could lead to a significant performance increase. For instance, we may want to serve content
to a group of users by taking advantage of an underlying network of social relationships among them.
In this talk, I’ll review very recent research activity in the context of stochastic bandit algorithms
where the network of users is either known beforehand, or has to be inferred on the fly based on
observed data. I’ll present algorithms, associated analyses, and empirical evidence on both synthetic
and real-world data.
