pith. sign in

arxiv: 1702.02849 · v1 · pith:42XA54BVnew · submitted 2017-02-09 · 💻 cs.LG · stat.ML

Coordinated Online Learning With Applications to Learning User Preferences

classification 💻 cs.LG stat.ML
keywords learningonlinealgorithmconvexcoollearnerspreferencesrelationship
0
0 comments X
read the original abstract

We study an online multi-task learning setting, in which instances of related tasks arrive sequentially, and are handled by task-specific online learners. We consider an algorithmic framework to model the relationship of these tasks via a set of convex constraints. To exploit this relationship, we design a novel algorithm -- COOL -- for coordinating the individual online learners: Our key idea is to coordinate their parameters via weighted projections onto a convex set. By adjusting the rate and accuracy of the projection, the COOL algorithm allows for a trade-off between the benefit of coordination and the required computation/communication. We derive regret bounds for our approach and analyze how they are influenced by these trade-off factors. We apply our results on the application of learning users' preferences on the Airbnb marketplace with the goal of incentivizing users to explore under-reviewed apartments.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.