Timezone: »

 
Poster
Bayesian Optimization with Exponential Convergence
Kenji Kawaguchi · Leslie Kaelbling · Tomás Lozano-Pérez

Mon Dec 07 04:00 PM -- 08:59 PM (PST) @ 210 C #83

This paper presents a Bayesian optimization method with exponential convergence without the need of auxiliary optimization and without the delta-cover sampling. Most Bayesian optimization methods require auxiliary optimization: an additional non-convex global optimization problem, which can be time-consuming and hard to implement in practice. Also, the existing Bayesian optimization method with exponential convergence requires access to the delta-cover sampling, which was considered to be impractical. Our approach eliminates both requirements and achieves an exponential convergence rate.

Author Information

Kenji Kawaguchi (MIT)
Leslie Kaelbling (MIT)
Tomás Lozano-Pérez (MIT)

More from the Same Authors